INDEX

Explanations

references to licensing and software distribution terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 gilt

-0.15

-0.14

 bitter

-0.14

da

-0.14

illi

-0.14

lav

-0.13

 Prosec

-0.13

POSITIVE LOGITS

Ð¸Ñī

0.15

defgroup

0.15

Ð³Ñĥ

0.15

SSIP

0.15

 agre

0.14

.scalablytyped

0.14

æĻĵ

0.14

ALS

0.14

$MESS

0.14

íĥģ

0.14

Activations Density 0.004%

references to licensing and software distribution terms

No Comments

No Known Activations