INDEX

Explanations

references to solutions and problem-solving concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

itable

-0.17

riere

-0.17

ori

-0.16

loor

-0.15

nea

-0.15

lander

-0.14

orman

-0.14

.yy

-0.14

lij

-0.14

outs

-0.14

POSITIVE LOGITS

 provider

0.27

 providers

0.25

aries

0.23

provider

0.23

-provider

0.23

ary

0.22

 Provider

0.22

æĸ¹æ¡Ī

0.21

 Providers

0.20

Activations Density 0.044%

references to solutions and problem-solving concepts

No Comments

No Known Activations