INDEX

Explanations

mentions of news reporting and articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 táº¡p

-0.17

Ä±rak

-0.15

 journal

-0.15

PBS

-0.15

 Ø§ÙħÛĮØ¯

-0.15

 pamph

-0.14

 journals

-0.14

iros

-0.14

lesen

-0.14

inson

-0.14

POSITIVE LOGITS

 story

0.55

 stories

0.48

 Story

0.40

story

0.40

Story

0.38

.story

0.38

 STORY

0.36

 Stories

0.35

-story

0.35

stories

0.34

Activations Density 0.122%

mentions of news reporting and articles

No Comments

No Known Activations