INDEX

Explanations

numerical data and symbols related to measurements and results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ð¼Ð°Ð·

-0.15

vard

-0.15

lar

-0.14

lej

-0.13

unden

-0.13

okus

-0.13

Î²Î¬

-0.13

 Grill

-0.13

dez

-0.13

 elig

-0.13

POSITIVE LOGITS

 Campos

0.15

Dai

0.15

dac

0.14

Cab

0.14

ko

0.14

RC

0.14

ayÄ±

0.14

dots

0.14

Dak

0.14

0.13

Activations Density 0.016%

numerical data and symbols related to measurements and results

No Comments

No Known Activations