INDEX

Explanations

discussions related to community issues and interactions among individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

lest

-0.14

Ø§Ø·

-0.13

NESS

-0.13

sov

-0.13

Ã£i

-0.13

elez

-0.13

EFA

-0.13

 ì²ĺ

-0.13

 Brace

-0.13

onian

-0.13

POSITIVE LOGITS

phinx

0.16

cca

0.16

iej

0.15

oola

0.15

trand

0.15

ÏĢÏīÏĤ

0.14

 Kang

0.14

owski

0.14

 æĽ

0.14

icari

0.13

Activations Density 0.361%

discussions related to community issues and interactions among individuals

No Comments

No Known Activations