INDEX

Explanations

geographical designations and regional acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

heck

-0.20

ities

-0.18

BU

-0.16

Nah

-0.15

mx

-0.15

uiten

-0.15

olar

-0.15

ocl

-0.15

 Orbit

-0.15

undler

-0.15

POSITIVE LOGITS

ernal

0.16

bÃŃ

0.16

INLINE

0.15

 plÃ¡

0.15

Ã´m

0.15

nid

0.15

tin

0.14

tin

0.14

 shel

0.14

 tÃŃnh

0.14

Activations Density 0.083%

geographical designations and regional acronyms

No Comments

No Known Activations