INDEX

Explanations

numeric distances and measurements related to location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

idon

-0.15

Ord

-0.15

INGTON

-0.15

licate

-0.14

yles

-0.14

deb

-0.13

ibs

-0.13

 dÃ¼ÅŁÃ¼r

-0.13

ailer

-0.13

inox

-0.13

POSITIVE LOGITS

Å¡ov

0.17

affer

0.15

 åĨĨ

0.14

iá»ģn

0.14

avec

0.14

PRS

0.14

ager

0.13

æħ¶

0.13

 ãĥĢ

0.13

uth

0.13

Activations Density 0.002%

numeric distances and measurements related to location

No Comments

No Known Activations