INDEX

Explanations

symbols and specific numerical or formatting patterns within 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 @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

angel

-0.18

ALI

-0.17

ESCO

-0.16

ippi

-0.16

URED

-0.16

 bench

-0.15

 Bench

-0.15

_lineno

-0.15

 Pare

-0.15

estre

-0.15

POSITIVE LOGITS

 Century

0.15

agnostics

0.15

alt

0.14

ajÄħc

0.14

agine

0.14

 Pistol

0.14

ivas

0.14

ynom

0.14

 Double

0.14

Activations Density 0.005%

symbols and specific numerical or formatting patterns within the text

No Comments

No Known Activations