INDEX

Explanations

percentage values in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

unan

-0.17

ambi

-0.16

acin

-0.15

onet

-0.15

onaut

-0.15

stown

-0.15

mant

-0.15

deer

-0.15

HO

-0.15

spiel

-0.14

POSITIVE LOGITS

elow

0.16

ilio

0.16

ventional

0.15

ÑıÐ¶

0.15

atus

0.14

infeld

0.14

Dot

0.14

0.13

ourses

0.13

 blow

0.13

Activations Density 0.004%

percentage values in the text

No Comments

No Known Activations