INDEX

Explanations

references to automotive design features and specifications

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

 ÂŃ

-0.18

 âĢª

-0.17

ulumi

-0.16

apter

-0.15

ovice

-0.14

 “âĢ¦

-0.14

qus

-0.14

ÙĳÙĲ

-0.14

 Canter

-0.14

ä¿Ĭ

-0.14

POSITIVE LOGITS

 contador

0.22

,''

0.17

"a

0.16

|}↵

0.16

 Additionally

0.16

 ë¨¹

0.16

 .↵

0.16

jel

0.16

Activations Density 0.042%

references to automotive design features and specifications

No Comments

No Known Activations