INDEX

Explanations

references to time and results in a dataset or script

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

elves

-0.17

ivar

-0.15

Nie

-0.15

 Figure

-0.15

ph

-0.14

Hew

-0.14

is

-0.14

 remote

-0.14

timer

-0.14

POSITIVE LOGITS

UIG

0.15

voj

0.15

_INLINE

0.15

lds

0.14

zac

0.14

Ø§ÛĮØ²

0.14

onen

0.14

 ConnectionState

0.14

eyen

0.14

æ¬²

0.14

Activations Density 0.031%

references to time and results in a dataset or script

No Comments

No Known Activations