INDEX

Explanations

instances of the word "so" used in various contexts

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

ibar

-0.17

olia

-0.16

 å®¶

-0.15

ibo

-0.15

combe

-0.14

inqu

-0.14

 dolu

-0.14

idis

-0.14

eltas

-0.13

ipher

-0.13

POSITIVE LOGITS

 naturally

0.22

 much

0.21

far

0.21

oner

0.20

aking

0.19

aked

0.18

aring

0.18

 Much

0.18

Much

0.18

 often

0.17

Activations Density 0.053%

instances of the word "so" used in various contexts

No Comments

No Known Activations

instances of the word "so" used in various contexts

No Comments

No Known Activations