INDEX

Explanations

instances of the word "talk" and its variations, indicating a focus on communication or discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 fully

-0.18

-0.16

uz

-0.16

/full

-0.15

bat

-0.15

fort

-0.15

ova

-0.15

ful

-0.15

fully

-0.15

omen

-0.15

POSITIVE LOGITS

 about

0.29

 smack

0.23

 ABOUT

0.23

_about

0.21

-about

0.20

 despre

0.20

 About

0.19

about

0.19

-talk

0.18

About

0.18

Activations Density 0.041%

instances of the word "talk" and its variations, indicating a focus on communication or discussion

No Comments

No Known Activations