INDEX

Explanations

the word "this" 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 @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

å¦Ĥä¸ĭ

-0.16

 this

-0.16

this

-0.15

 nÃły

-0.15

lems

-0.15

uel

-0.15

ts

-0.14

 ÑįÑĤÐ¾

-0.14

audi

-0.14

/rc

-0.14

POSITIVE LOGITS

 particular

0.34

/th

0.33

/her

0.23

 PARTICULAR

0.21

curity

0.18

guy

0.17

 particul

0.17

ìłĢ

0.16

Guy

0.16

 kind

0.16

Activations Density 0.453%

the word "this" in various contexts

No Comments

No Known Activations