INDEX

Explanations

mentions of lawsuits and legal actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Prosec

-0.16

çĬ¯

-0.16

 Crimes

-0.16

 Prosecutor

-0.15

á»ĳc

-0.15

 electorate

-0.15

ç½ª

-0.15

om

-0.15

åĪº

-0.14

enance

-0.14

POSITIVE LOGITS

lit

0.47

 suits

0.45

 lawsuit

0.43

 lawsuits

0.42

 suit

0.41

 legal

0.40

 litigation

0.38

lit

0.37

Lit

0.37

sue

0.36

Activations Density 0.700%

mentions of lawsuits and legal actions

No Comments

No Known Activations