INDEX

Explanations

references to "air"

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

inel

-0.16

connexion

-0.16

oldown

-0.15

odos

-0.15

ahoma

-0.15

ENCIL

-0.14

yny

-0.14

kip

-0.14

isko

-0.14

ë¥

-0.14

POSITIVE LOGITS

urer

0.16

ship

0.15

 basket

0.15

axy

0.14

ÑĥÐ»Ð¸

0.14

sha

0.14

 pearls

0.13

æĹ

0.13

 confined

0.13

aro

0.13

Activations Density 0.015%

references to "air"

No Comments

No Known Activations