INDEX

Explanations

proper nouns and specific entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ÄĽr

-0.17

ANEL

-0.15

hausen

-0.15

anel

-0.15

thood

-0.15

veled

-0.15

boru

-0.14

ureau

-0.14

ine

-0.14

ahoo

-0.14

POSITIVE LOGITS

 shell

0.15

 game

0.15

arda

0.14

 Game

0.14

ÐµÑģÑĤÐ¸

0.14

ientos

0.14

hoff

0.14

Callbacks

0.14

 jint

0.13

udder

0.13

Activations Density 0.050%

proper nouns and specific entities

No Comments

No Known Activations