INDEX

Explanations

references and discussions about legal concepts and laws

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.17

olini

-0.17

aurus

-0.16

ity

-0.16

Øª

-0.15

ressing

-0.15

Ð´Ðµ

-0.15

kÃ¡

-0.15

leitung

-0.15

POSITIVE LOGITS

fully

0.33

fulness

0.25

rence

0.25

yer

0.22

renc

0.21

/reg

0.21

erence

0.21

fare

0.21

-ab

0.20

yers

0.19

Activations Density 0.053%

references and discussions about legal concepts and laws

No Comments

No Known Activations