INDEX

Explanations

references to geographical and territorial elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

æģ

-0.16

asl

-0.15

 clos

-0.14

 Shak

-0.14

pak

-0.14

Mig

-0.14

nar

-0.14

ucci

-0.13

 provid

-0.13

Dod

-0.13

POSITIVE LOGITS

atown

0.17

aye

0.17

embr

0.15

çĶ·åŃĲ

0.15

.rad

0.15

Ø¨Ø³

0.14

 derp

0.14

rowsable

0.14

.comp

0.14

benh

0.14

Activations Density 0.000%

references to geographical and territorial elements

No Comments

No Known Activations