INDEX

Explanations

percentage values and indicators of statistics

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

ilee

-0.15

linger

-0.15

pte

-0.14

ossier

-0.14

 Years

-0.14

 everywhere

-0.14

ä¹±

-0.14

tant

-0.14

 tonight

-0.13

POSITIVE LOGITS

 monthly

0.69

 weekly

0.60

monthly

0.59

 quarterly

0.56

 Monthly

0.56

 regular

0.56

Monthly

0.54

weekly

0.52

regular

0.48

 Weekly

0.47

Activations Density 0.005%

percentage values and indicators of statistics

No Comments

No Known Activations