INDEX

Explanations

terms associated with destruction and demolition processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

oog

-0.16

ialized

-0.15

rawer

-0.15

MeasureSpec

-0.15

Ø¯

-0.15

rop

-0.15

cot

-0.15

Ð³Ð°Ð»

-0.15

erland

-0.14

aeda

-0.14

POSITIVE LOGITS

inha

0.16

isto

0.16

zer

0.15

aul

0.15

uet

0.14

esti

0.14

ä¸¶

0.14

vat

0.14

&amp

0.14

lum

0.14

Activations Density 0.023%

terms associated with destruction and demolition processes

No Comments

No Known Activations