INDEX

Explanations

instances of the word "to" 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

vala

-0.18

RICT

-0.16

aring

-0.15

ahoma

-0.15

ardash

-0.14

gettext

-0.14

 itself

-0.14

Ð½Ð¸Ð½Ð°

-0.14

oÅ¾

-0.14

Ð¾Ð³Ð¾Ð´

-0.14

POSITIVE LOGITS

see

0.35

 visit

0.28

see

0.26

 town

0.22

 church

0.21

visit

0.20

bed

0.20

 court

0.20

See

0.20

 work

0.19

Activations Density 0.133%

instances of the word "to" in various contexts

No Comments

No Known Activations