INDEX

Explanations

transitions indicating rephrased explanations or clarifications

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

ucht

-0.14

ntag

-0.14

ubu

-0.14

ujet

-0.14

xin

-0.14

ileen

-0.14

lez

-0.14

ÏĥÏĦÎ®

-0.14

atsu

-0.13

astreet

-0.13

POSITIVE LOGITS

 words

0.52

words

0.43

 Words

0.34

.words

0.33

_words

0.32

Words

0.31

 palabras

0.28

 word

0.28

wards

0.27

 wards

0.27

Activations Density 0.013%

transitions indicating rephrased explanations or clarifications

No Comments

No Known Activations