INDEX

Explanations

contact information and references to support and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Å¡ku

-0.15

uhn

-0.15

bsites

-0.14

aign

-0.14

ikipedia

-0.14

ourt

-0.13

.githubusercontent

-0.13

ngen

-0.13

Deb

-0.13

.ibm

-0.13

POSITIVE LOGITS

0.30

@index

0.22

@api

0.21

(at

0.21

@Id

0.21

[at

0.21

@s

0.21

@show

0.21

@property

0.20

0.19

Activations Density 0.033%

contact information and references to support and services

No Comments

No Known Activations