INDEX

Explanations

words related to large scale or extensive areas

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

 OnTrigger

-0.15

lectric

-0.15

eldo

-0.14

apanese

-0.14

lessly

-0.14

dyby

-0.14

eut

-0.14

dust

-0.14

_PUSHDATA

-0.14

POSITIVE LOGITS

 Ballard

0.17

 spread

0.15

irm

0.14

á¿Ĩ

0.14

 Reform

0.14

Ø§Ø¯Ø§

0.14

Od

0.14

0.13

fone

0.13

oes

0.13

Activations Density 0.007%

words related to large scale or extensive areas

No Comments

No Known Activations