INDEX

Explanations

proper names and specific nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

neider

-0.13

âĢĮÙ¾Ø¯ÛĮØ§ÛĮ

-0.13

antino

-0.13

.nlm

-0.13

untos

-0.12

Ãª

-0.12

omik

-0.12

ombine

-0.12

_ASYNC

-0.12

QE

-0.12

POSITIVE LOGITS

-w

0.56

_w

0.47

-W

0.45

.w

0.43

0.39

*w

0.38

_W

0.38

>w

0.36

+w

0.35

,w

0.34

Activations Density 0.440%

proper names and specific nouns

No Comments

No Known Activations