INDEX

Explanations

references to notable newspapers or media outlets in 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

athom

-0.16

CLUDE

-0.14

acman

-0.14

illance

-0.14

çľī

-0.13

Cov

-0.13

_RESP

-0.13

dit

-0.13

abar

-0.13

clipse

-0.13

POSITIVE LOGITS

ipt

0.18

 journal

0.17

 Journal

0.17

 subt

0.16

ç«ĭ

0.15

 jour

0.15

0.14

áº£o

0.14

zd

0.14

 outlet

0.14

Activations Density 0.222%

references to notable newspapers or media outlets in the text

No Comments

No Known Activations