INDEX

Explanations

mentions of cameras and related imagery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ffen

-0.17

uts

-0.16

uer

-0.15

anny

-0.15

ment

-0.14

sert

-0.14

ave

-0.14

lander

-0.14

ouch

-0.14

angered

-0.13

POSITIVE LOGITS

esium

0.16

Ø§Ø³Ø¨

0.15

 Ð¿Ð¸ÑĤ

0.15

******↵

0.15

zeÅĪ

0.14

akit

0.14

rys

0.14

Cha

0.14

umba

0.14

elmet

0.14

Activations Density 0.008%

mentions of cameras and related imagery

No Comments

No Known Activations