INDEX

Explanations

references to "ponies" or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

-0.17

eum

-0.16

ALSE

-0.16

es

-0.15

ei

-0.15

ìĺ¥

-0.14

vise

-0.14

tat

-0.14

eks

-0.14

POSITIVE LOGITS

ksiyon

0.20

emin

0.17

ctions

0.17

ì¦Ī

0.17

uts

0.17

ny

0.16

du

0.16

nish

0.16

ction

0.16

nder

0.16

Activations Density 0.015%

references to "ponies" or related terms

No Comments

No Known Activations