INDEX

Explanations

words related to viewer or reader engagement in artistic or literary contexts

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

ahn

-0.17

ety

-0.15

 Ø´Ø±ÙĤÛĮ

-0.14

kÃ¼n

-0.14

apper

-0.14

ãĥĥãĤ·ãĥ¥

-0.13

 Developers

-0.13

iren

-0.13

BuilderFactory

-0.13

icerca

-0.13

POSITIVE LOGITS

 readers

0.85

 reader

0.85

 viewers

0.73

 viewer

0.69

 Readers

0.66

 audience

0.61

reader

0.61

 Reader

0.59

 audiences

0.57

-reader

0.55

Activations Density 0.276%

words related to viewer or reader engagement in artistic or literary contexts

No Comments

No Known Activations