INDEX

Explanations

references to geographic locations and water bodies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 AssemblyVersion

-0.17

landa

-0.14

alytics

-0.14

avan

-0.14

STD

-0.14

Ci

-0.13

IRS

-0.13

imary

-0.13

åºŃ

-0.13

åĩĨ

-0.13

POSITIVE LOGITS

waukee

0.23

aukee

0.23

quan

0.23

 Indians

0.21

ippi

0.19

 Indian

0.19

qua

0.19

quam

0.19

aw

0.18

oodle

0.18

Activations Density 0.093%

references to geographic locations and water bodies

No Comments

No Known Activations