INDEX

Explanations

terms related to legal processes and procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ALLY

-0.23

ally

-0.23

ially

-0.20

sWith

-0.19

 cons

-0.17

ifies

-0.15

antly

-0.15

pdata

-0.15

cuts

-0.15

 Cons

-0.15

POSITIVE LOGITS

ishment

0.24

ution

0.23

ipation

0.23

ination

0.23

iting

0.22

ulation

0.22

ited

0.21

achment

0.20

gement

0.20

lement

0.19

Activations Density 0.070%

terms related to legal processes and procedures

No Comments

No Known Activations