INDEX

Explanations

phrases related to significant events, transformations, or impactful moments

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

 found

-0.16

found

-0.16

woke

-0.15

Found

-0.15

è¦ĭ

-0.15

å°ĩ

-0.15

-found

-0.14

_found

-0.14

vanced

-0.14

 Found

-0.14

POSITIVE LOGITS

 emerge

0.36

 evolve

0.34

 unfold

0.34

 happen

0.30

 arise

0.30

 occur

0.30

 disappear

0.29

 explode

0.29

 arrive

0.28

 come

0.28

Activations Density 0.306%

phrases related to significant events, transformations, or impactful moments

No Comments

No Known Activations