INDEX

Explanations

references to news articles and their content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ä±rak

-0.17

AdapterManager

-0.15

iros

-0.15

gow

-0.14

Subset

-0.14

lector

-0.14

itunes

-0.14

nyder

-0.13

 IMDb

-0.13

_NPC

-0.13

POSITIVE LOGITS

 story

0.73

 stories

0.66

story

0.56

 Story

0.54

Story

0.53

 Stories

0.50

 STORY

0.50

-story

0.49

stories

0.48

.story

0.47

Activations Density 0.244%

references to news articles and their content

No Comments

No Known Activations