INDEX

Explanations

geographical directions and 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 western

-0.22

 west

-0.19

 eastern

-0.19

 northern

-0.18

 southern

-0.17

rix

-0.16

ormap

-0.16

aurant

-0.15

 south

-0.15

ilyn

-0.15

POSITIVE LOGITS

NE

0.16

nw

0.15

 Subscribe

0.14

 overhead

0.14

 nerve

0.14

variable

0.14

 McCorm

0.14

 Howell

0.13

)prepare

0.13

Sector

0.13

Activations Density 0.007%

geographical directions and related terms

No Comments

No Known Activations