INDEX

Explanations

instances of the word "only" and its variations, emphasizing exclusivity or limitation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 both

-0.18

isco

-0.15

oro

-0.15

 something

-0.15

both

-0.14

 exact

-0.14

eer

-0.14

ron

-0.14

POSITIVE LOGITS

//{{

0.20

 upon

0.19

iggs

0.17

upon

0.16

 because

0.16

 forKey

0.16

$fdata

0.14

Î¯Îº

0.14

FTA

0.14

 porque

0.14

Activations Density 0.103%

instances of the word "only" and its variations, emphasizing exclusivity or limitation

No Comments

No Known Activations