INDEX

Explanations

references to safety issues or product recalls

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

Ð»ÑİÐ´

-0.15

strand

-0.14

.spatial

-0.14

ysa

-0.14

lections

-0.14

 Ministers

-0.14

 ká»·

-0.13

 frei

-0.13

dÃ¼l

-0.13

è¾ĳ

-0.13

POSITIVE LOGITS

 bills

0.41

 legislation

0.39

 House

0.39

 bill

0.38

 passage

0.37

 Congress

0.35

 Senate

0.33

 Bills

0.31

Sen

0.30

 Legislation

0.30

Activations Density 0.953%

references to safety issues or product recalls

No Comments

No Known Activations