INDEX

Explanations

references to authors and literary works, particularly notable ones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

DMI

-0.17

 Bout

-0.14

cken

-0.14

deen

-0.14

_pitch

-0.14

etsk

-0.14

 wire

-0.14

tember

-0.13

 shoe

-0.13

bef

-0.13

POSITIVE LOGITS

Blo

0.28

 Wool

0.27

 Joyce

0.27

Blo

0.24

 Virginia

0.24

Virginia

0.23

Joy

0.23

 Bloom

0.20

 stream

0.18

 Pound

0.18

Activations Density 0.013%

references to authors and literary works, particularly notable ones

No Comments

No Known Activations