INDEX

Explanations

numerical values associated with measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

erb

-0.15

ï¿

-0.15

.ends

-0.15

 setattr

-0.15

UST

-0.14

assi

-0.14

parm

-0.14

cd

-0.14

 Carry

-0.14

isten

-0.14

POSITIVE LOGITS

ÎºÎ¬

0.17

impse

0.16

 Sunder

0.16

sock

0.16

acente

0.15

ambda

0.15

opol

0.15

WARE

0.14

 æ¬

0.14

Activations Density 0.000%

numerical values associated with measures

No Comments

No Known Activations