INDEX

Explanations

references to specific places or events

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

caret

-0.17

odont

-0.16

ikat

-0.16

íĥģ

-0.15

WV

-0.15

 Loch

-0.15

uhan

-0.14

.study

-0.14

rzy

-0.14

illus

-0.14

POSITIVE LOGITS

SD

0.39

SD

0.38

San

0.38

 Padres

0.36

SDS

0.35

 Chargers

0.33

 Qualcomm

0.32

sd

0.32

San

0.32

Activations Density 0.042%

references to specific places or events

No Known Activations