INDEX

Explanations

words related to geographic locations and their significance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

wald

-0.20

odie

-0.16

ÐµÐ½ÑĮ

-0.16

uron

-0.16

ÙĤÙģ

-0.16

STRU

-0.15

yscale

-0.15

-anchor

-0.15

åº§

-0.14

-Identifier

-0.14

POSITIVE LOGITS

rawer

0.16

 duty

0.14

acios

0.14

ìłķë¶Ģ

0.14

Ã³z

0.14

Cad

0.14

apan

0.14

ŀæĢ§

0.14

 Sind

0.13

Cad

0.13

Activations Density 0.114%

words related to geographic locations and their significance

No Comments

No Known Activations