INDEX

Explanations

variations of the pronoun "he" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

vyk

-0.15

TestCategory

-0.15

ray

-0.15

ibase

-0.15

uji

-0.14

cf

-0.14

Wel

-0.14

esc

-0.14

apult

-0.14

sm

-0.14

POSITIVE LOGITS

inner

0.18

hi

0.17

asers

0.17

Ã¶ff

0.17

erb

0.16

asmus

0.16

inn

0.16

igon

0.16

immer

0.15

aser

0.15

Activations Density 0.007%

variations of the pronoun "he" in different contexts

No Comments

No Known Activations