INDEX

Explanations

references to car brands and specific vehicle models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

elow

-0.16

[sizeof

-0.15

Ð»Ð¸Ð½

-0.15

nze

-0.15

IRD

-0.14

 Seymour

-0.14

asio

-0.14

-0.13

Ä©

-0.13

å»

-0.13

POSITIVE LOGITS

innen

0.17

ux

0.16

stin

0.16

DataURL

0.15

idge

0.15

untu

0.15

ocker

0.15

 Parts

0.14

stance

0.14

ander

0.14

Activations Density 0.215%

references to car brands and specific vehicle models

No Comments

No Known Activations