INDEX

Explanations

mention of influential figures or concepts in professional or academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

lds

-0.17

ocache

-0.14

 Japanese

-0.14

orean

-0.14

 Moines

-0.14

odzi

-0.14

Harness

-0.14

ampler

-0.14

JNI

-0.14

Japanese

-0.13

POSITIVE LOGITS

Ace

0.20

Ace

0.17

 Captain

0.17

 Kurum

0.16

 teamwork

0.16

ace

0.16

Gen

0.16

gen

0.15

 Shadow

0.15

VS

0.15

Activations Density 0.003%

mention of influential figures or concepts in professional or academic contexts

No Comments

No Known Activations