INDEX

Explanations

references to unnamed individuals or things, particularly in a context of commentary or analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ãģİ

-0.14

emas

-0.14

à¹Ģà¸¥à¸¢

-0.13

ento

-0.13

Ð¾Ð±Ð¾Ð²

-0.13

hunter

-0.13

asad

-0.13

éļª

-0.13

anders

-0.13

 Nearly

-0.13

POSITIVE LOGITS

 unnamed

0.54

 unidentified

0.51

 unknown

0.47

 unspecified

0.47

 anonymous

0.44

 Unknown

0.43

unknown

0.43

Unknown

0.41

 Anonymous

0.40

Anonymous

0.39

Activations Density 0.191%

references to unnamed individuals or things, particularly in a context of commentary or analysis

No Comments

No Known Activations