INDEX

Explanations

variations of the word "incongruous" and its forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ç°

-0.18

styleType

-0.16

@$_

-0.16

oky

-0.15

dle

-0.15

izzo

-0.15

pty

-0.15

adlo

-0.15

ColorBrush

-0.15

ìļ´ëį°

-0.14

POSITIVE LOGITS

sequential

0.25

athom

0.18

ce

0.18

clusive

0.18

preh

0.17

uous

0.17

gr

0.17

 sequential

0.17

ushima

0.16

UMENT

0.15

Activations Density 0.011%

variations of the word "incongruous" and its forms

No Comments

No Known Activations