INDEX

Explanations

lists and items that require organization or clarification

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Terra

-0.14

 Bang

-0.14

berger

-0.14

 trailers

-0.13

 uniforms

-0.13

 atmosphere

-0.13

ilde

-0.13

 tubes

-0.13

 misc

-0.13

lette

-0.13

POSITIVE LOGITS

 list

0.30

list

0.26

 lists

0.25

 List

0.25

-list

0.23

 listing

0.22

_list

0.21

List

0.21

ãĥªãĤ¹ãĥĪ

0.20

.list

0.20

Activations Density 0.252%

lists and items that require organization or clarification

No Known Activations