INDEX

Explanations

occurrences of the word "in" and its various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ume

-0.15

anga

-0.15

ering

-0.14

Ë

-0.14

ÑĢÐµÑī

-0.13

ãĤ¦ãĥĪ

-0.13

arga

-0.13

é«ĺæ¸ħ

-0.13

ard

-0.13

mas

-0.13

POSITIVE LOGITS

 remarks

0.27

 statements

0.27

 comments

0.26

 statement

0.23

 interviews

0.22

 separate

0.20

 response

0.20

 entrev

0.20

remarks

0.19

statements

0.19

Activations Density 0.093%

occurrences of the word "in" and its various forms

No Comments

No Known Activations