INDEX

Explanations

terms related to documentation and files, particularly in a programming or technical context

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

json

-0.22

_json

-0.21

joint

-0.20

Json

-0.19

/job

-0.19

 Jewish

-0.19

 joint

-0.18

jud

-0.18

 judgment

-0.18

_joint

-0.18

POSITIVE LOGITS

ÅĽli

0.24

venile

0.24

 Báº£n

0.23

neys

0.20

uxtap

0.19

stice

0.19

assic

0.18

oints

0.18

ovah

0.18

upyter

0.17

Activations Density 0.644%

terms related to documentation and files, particularly in a programming or technical context

No Comments

No Known Activations