INDEX

Explanations

references and citations in academic or research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ķìĿ¸

-0.15

ousy

-0.15

ervo

-0.14

adera

-0.14

panion

-0.14

UpdatedAt

-0.14

ritel

-0.14

ASP

-0.14

aders

-0.14

hob

-0.13

POSITIVE LOGITS

loc

0.20

 Exercise

0.19

Cor

0.18

cul

0.17

Remark

0.16

ISIBLE

0.16

 proves

0.16

 Remark

0.16

Exercise

0.16

 exercise

0.16

Activations Density 0.131%

references and citations in academic or research contexts

No Comments

No Known Activations