INDEX

Explanations

questions and inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Ã³r

-0.17

 Mines

-0.17

OTO

-0.15

oto

-0.15

éŁ¿

-0.15

ajo

-0.14

 cases

-0.14

amps

-0.14

anna

-0.14

POSITIVE LOGITS

osy

0.19

ãģķãģ¾

0.15

RET

0.15

toMatchSnapshot

0.15

@Spring

0.15

avou

0.15

libft

0.15

Å¯st

0.14

ovit

0.14

 cref

0.14

Activations Density 0.115%

questions and inquiries

No Comments

No Known Activations