INDEX

Explanations

references to mysteries or enigmatic subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

nev

-0.18

beits

-0.16

enn

-0.16

.scalablytyped

-0.16

ÐµÐºÑģÐ¸

-0.15

atty

-0.15

ãģįãģŁ

-0.15

uckles

-0.14

ales

-0.14

à¹Ħà¸«à¸Ļ

-0.14

POSITIVE LOGITS

-solving

0.26

 solved

0.21

 surrounding

0.18

/conf

0.18

 Solver

0.18

kowski

0.18

 solver

0.18

 surrounds

0.18

 solving

0.17

_solver

0.17

Activations Density 0.048%

references to mysteries or enigmatic subjects

No Comments

No Known Activations