INDEX

Explanations

references to artistic works or creators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ã³c

-0.15

icode

-0.15

 pornost

-0.15

lda

-0.15

amble

-0.15

_Tis

-0.15

ÐµÐ»ÑĮÐ½Ð¾

-0.15

oader

-0.15

oppable

-0.15

.TabIndex

-0.15

POSITIVE LOGITS

0.18

0.16

 authorities

0.15

0.14

as

0.14

 Test

0.14

Ree

0.14

.html

0.14

 Rosen

0.14

Activations Density 0.002%

references to artistic works or creators

No Comments

No Known Activations