INDEX

Explanations

questions posed in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

entar

-0.16

errar

-0.15

ented

-0.15

ent

-0.14

iller

-0.14

ifter

-0.14

ublisher

-0.14

omor

-0.14

anity

-0.13

Ã£n

-0.13

POSITIVE LOGITS

 better

0.31

better

0.23

 mejor

0.21

 else

0.20

 could

0.19

Better

0.18

 more

0.17

 Better

0.17

do

0.17

could

0.16

Activations Density 0.043%

questions posed in the text

No Comments

No Known Activations