INDEX

Explanations

geographical and locational descriptors

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

uld

-0.16

uhan

-0.15

apia

-0.14

cht

-0.14

Dot

-0.14

ãģĻãģİ

-0.14

Ĭ

-0.14

Ã³d

-0.14

entiful

-0.14

craft

-0.13

POSITIVE LOGITS

0.17

Ø±Ø§Øª

0.16

inel

0.15

 $("#"

0.15

aur

0.14

AREST

0.14

ewan

0.14

 $('#'

0.14

 Orwell

0.14

Activations Density 0.055%

geographical and locational descriptors

No Comments

No Known Activations