INDEX

Explanations

references to regulatory changes and restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

hai

-0.16

ÅĻes

-0.15

erten

-0.14

ZA

-0.14

 attendance

-0.14

pitch

-0.14

pixel

-0.14

Î¼Î¼Îµ

-0.14

iki

-0.14

 McCart

-0.13

POSITIVE LOGITS

quin

0.17

 relax

0.15

 allow

0.15

 Allow

0.15

Allow

0.14

 ÙģØªØŃ

0.14

undry

0.14

oller

0.14

.physics

0.14

arkin

0.14

Activations Density 0.281%

references to regulatory changes and restrictions

No Comments

No Known Activations