INDEX

Explanations

punctuation and markers that indicate speech or quotes

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

 âĢŀ

-0.23

 “âĢ¦

-0.23

 (“

-0.23

`),↵

-0.17

okt

-0.16

 ******************************************************************************↵

-0.16

“

-0.16

htub

-0.15

 (Â«

-0.15

sonian

-0.15

POSITIVE LOGITS

,"

0.21

":

0.18

âĢ³

0.18

"↵

0.17

"↵↵

0.16

","

0.14

Ã¤

0.14

AndWait

0.14

":"

0.14

":""

0.14

Activations Density 0.299%

punctuation and markers that indicate speech or quotes

No Comments

No Known Activations