INDEX

Explanations

words associated with physical positioning and arrangement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

isms

-0.16

 located

-0.15

 Mein

-0.15

Âł

-0.15

igo

-0.14

Ļ¨

-0.14

POSITIVE LOGITS

.pretty

0.18

 geschichten

0.17

_vlog

0.17

KHTML

0.16

ANTE

0.16

=-=-=-=-

0.16

istrovstvÃŃ

0.16

ayacak

0.15

 gá»įn

0.15

ÄĮesk

0.15

Activations Density 0.115%

words associated with physical positioning and arrangement

No Comments

No Known Activations