INDEX

Explanations

references to governmental or organizational entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

allis

-0.18

aqu

-0.16

ervas

-0.15

zar

-0.15

_nth

-0.13

 consegu

-0.13

IL

-0.13

ãĤ¤ãĤ¹

-0.13

ancel

-0.13

idding

-0.13

POSITIVE LOGITS

%C

0.15

taÅŁ

0.14

aff

0.14

 Ð²Ð¾ÑĢ

0.14

osemite

0.14

à¹Ģ

0.13

UED

0.13

rape

0.13

 Harris

0.13

_tC

0.13

Activations Density 0.564%

references to governmental or organizational entities

No Comments

No Known Activations