INDEX

Explanations

instances of legal terminology and references to legal proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ghi

-0.17

 Doyle

-0.15

.=

-0.15

Ã¨les

-0.15

ngle

-0.15

Ã¼rn

-0.14

locks

-0.14

stÅĻed

-0.14

=A

-0.14

={

-0.14

POSITIVE LOGITS

Wid

0.18

wid

0.17

 benef

0.16

 Cove

0.16

POSIT

0.15

onders

0.15

 Flag

0.15

lay

0.15

 arms

0.15

 Coll

0.15

Activations Density 0.009%

instances of legal terminology and references to legal proceedings

No Comments

No Known Activations