INDEX

Explanations

references to biological classifications, specifically family names in taxonomy

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

igu

-0.17

 Ð·Ð²ÐµÑĢ

-0.14

oir

-0.14

-native

-0.14

onio

-0.14

ÑĮÑı

-0.14

isher

-0.13

.IsFalse

-0.13

DNA

-0.13

ylene

-0.13

POSITIVE LOGITS

cus

0.18

0.15

 ç¦

0.14

ullo

0.14

inks

0.13

cus

0.13

inds

0.13

ÐºÐ¾Ð³

0.13

ÑĤÐ°Ð¿

0.13

Activations Density 0.011%

references to biological classifications, specifically family names in taxonomy

No Comments

No Known Activations