INDEX

Explanations

phrases indicating newcomers or individuals who are seeking help or guidance

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

-0.18

 Bast

-0.15

 Current

-0.15

éĻµ

-0.15

gone

-0.15

 founding

-0.15

 Stokes

-0.14

at

-0.14

 Recent

-0.14

 Barber

-0.14

POSITIVE LOGITS

icode

0.18

 fold

0.17

 folds

0.15

 unfamiliar

0.15

fleet

0.15

yne

0.15

ushima

0.14

ANCH

0.14

ipay

0.14

agara

0.14

Activations Density 0.029%

phrases indicating newcomers or individuals who are seeking help or guidance

No Comments

No Known Activations