INDEX

Explanations

metadata or log-related entries in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ing

-0.19

ues

-0.18

of

-0.17

le

-0.15

of

-0.15

he

-0.14

 Jarvis

-0.14

 Woods

-0.14

its

-0.14

ould

-0.14

POSITIVE LOGITS

ronym

0.18

enor

0.15

_nth

0.15

dech

0.15

¶ģ

0.14

ìĹħì²´

0.14

Prostit

0.14

Backing

0.14

etros

0.14

insics

0.14

Activations Density 0.196%

metadata or log-related entries in a structured format

No Comments

No Known Activations