INDEX

Explanations

specific symbols or unusual characters in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 âĢ¯

-0.18

 COVID

-0.17

 ðŁĶ

-0.16

âĢį

-0.16

âĢ¯

-0.15

â

-0.15

COVID

-0.15

ðŁ

-0.15

abbix

-0.15

ï¸ı

-0.15

POSITIVE LOGITS

 fucking

0.34

 fuck

0.29

 fucks

0.29

sod

0.28

 fucked

0.28

 Fucking

0.28

 shit

0.27

 FUCK

0.27

 Fuck

0.27

 Fucked

0.26

Activations Density 0.029%

specific symbols or unusual characters in the text

No Comments

No Known Activations