INDEX

Explanations

references to the concept of "otherness" and distinctions between different groups or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.15

iaux

-0.14

getID

-0.14

istring

-0.14

 Ð¿Ð¾Ñģ

-0.13

Father

-0.13

 Spit

-0.13

ucha

-0.13

.SDK

-0.13

utter

-0.13

POSITIVE LOGITS

appen

0.18

etc

0.18

etc

0.16

ogue

0.15

icism

0.15

.IContainer

0.15

izm

0.14

sÄ±

0.14

dden

0.14

 Polly

0.14

Activations Density 0.047%

references to the concept of "otherness" and distinctions between different groups or categories

No Comments

No Known Activations