INDEX

Explanations

instances of the term "proof" and its various associations, particularly within scientific or conceptual contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

unch

-0.17

ê»ĺ

-0.15

uet

-0.15

-gnu

-0.14

vre

-0.14

gi

-0.14

arium

-0.14

Î½Î·

-0.14

 onRequest

-0.14

ughter

-0.14

POSITIVE LOGITS

reading

0.30

READING

0.17

reader

0.17

ëĭĿ

0.17

lessly

0.17

chor

0.17

read

0.17

nock

0.16

iness

0.16

/dis

0.16

Activations Density 0.015%

instances of the term "proof" and its various associations, particularly within scientific or conceptual contexts

No Comments

No Known Activations