INDEX

Explanations

phrases or constructs that emphasize comparison or simile

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

alls

-0.17

Ð¾ÑĢÐ¼

-0.17

ingt

-0.16

eters

-0.15

etary

-0.15

cott

-0.14

awe

-0.14

HORT

-0.14

 saja

-0.14

instein

-0.14

POSITIVE LOGITS

 follows

0.22

cribed

0.21

paragus

0.20

sembl

0.18

cert

0.17

-is

0.16

 having

0.15

 souÄįÃ¡st

0.14

dit

0.14

cribe

0.14

Activations Density 0.148%

phrases or constructs that emphasize comparison or simile

No Comments

No Known Activations