INDEX

Explanations

references to legal processes and regulatory requirements

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

doll

-0.19

 Diss

-0.19

 Doll

-0.18

dens

-0.18

dir

-0.17

reator

-0.17

_dicts

-0.17

digits

-0.17

deen

-0.17

Dies

-0.17

POSITIVE LOGITS

 David

1.15

 david

1.03

David

1.03

 Dave

0.86

Dav

0.79

Dave

0.72

 Davidson

0.71

dav

0.57

DA

0.55

DA

0.47

Activations Density 0.035%

references to legal processes and regulatory requirements

No Comments

No Known Activations