INDEX

Explanations

names of locations and geographical areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ules

-0.19

etooth

-0.15

aea

-0.15

ulin

-0.14

oss

-0.14

rau

-0.14

tractor

-0.14

vertising

-0.14

isci

-0.13

OURNAL

-0.13

POSITIVE LOGITS

-area

0.15

 city

0.15

.Â§

0.15

ocity

0.14

 City

0.14

 à¤¶à¤¹à¤°

0.14

-region

0.13

ngÃ¶r

0.13

TextWriter

0.13

city

0.13

Activations Density 0.749%

names of locations and geographical areas

No Comments

No Known Activations