INDEX

Explanations

references to locations and events related to community or culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

rete

-0.15

UnderTest

-0.14

 Ä°h

-0.14

ALCHEMY

-0.14

ixel

-0.14

æµİ

-0.13

argent

-0.13

yll

-0.13

à¸£à¸¡

-0.13

laws

-0.13

POSITIVE LOGITS

Ø¬Ø±

0.15

arning

0.15

enthal

0.14

obox

0.14

rikes

0.14

&id

0.14

*)_

0.14

Ø§ÛĮØ´

0.14

 Trib

0.13

 incon

0.13

Activations Density 0.035%

references to locations and events related to community or culture

No Comments

No Known Activations