INDEX

Explanations

phrases describing risks, challenges, and health concerns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

icot

-0.15

serrat

-0.15

itur

-0.15

laus

-0.14

FullPath

-0.14

deo

-0.14

lh

-0.14

£

-0.14

ool

-0.14

Ãºc

-0.14

POSITIVE LOGITS

 even

0.17

 sogar

0.17

0.16

 depending

0.15

le

0.15

even

0.15

 mÃªme

0.15

çĶļèĩ³

0.15

 incluso

0.15

plied

0.14

Activations Density 0.231%

phrases describing risks, challenges, and health concerns

No Comments

No Known Activations