INDEX

Explanations

references or citations in academic and research writing

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

iltr

-0.17

ares

-0.15

wan

-0.14

trand

-0.14

ooky

-0.14

ilers

-0.13

ãĥ³ãĥķ

-0.13

lij

-0.13

 Earth

-0.13

ached

-0.13

POSITIVE LOGITS

review

0.17

 reviews

0.16

zos

0.15

 reviewed

0.15

suming

0.15

 review

0.15

reviews

0.15

ifik

0.15

reau

0.14

Activations Density 0.008%

references or citations in academic and research writing

No Comments

No Known Activations