INDEX

Explanations

legal terminology and references to court decisions

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

aggi

-0.16

ans

-0.14

pron

-0.14

 Uncomment

-0.13

TE

-0.13

ending

-0.13

tain

-0.13

Ut

-0.13

 Claims

-0.13

Ã©mon

-0.13

POSITIVE LOGITS

 note

0.39

 noted

0.35

 pointed

0.32

 notes

0.32

 noting

0.29

_note

0.28

note

0.27

 point

0.25

-notes

0.25

.note

0.24

Activations Density 0.101%

legal terminology and references to court decisions

No Comments

No Known Activations