INDEX

Explanations

references to laws and legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

kÃ¡

-0.16

ity

-0.16

Ð´Ðµ

-0.15

olini

-0.15

Øª

-0.15

ately

-0.15

kle

-0.14

 Riley

-0.14

POSITIVE LOGITS

fully

0.32

rence

0.24

fulness

0.24

-ab

0.21

yer

0.21

/reg

0.20

renc

0.19

 enforcement

0.19

 Enforcement

0.19

fare

0.19

Activations Density 0.053%

references to laws and legal terminology

No Comments

No Known Activations