INDEX

Explanations

references to military corps, particularly the Marine Corps

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

etu

-0.16

ternet

-0.15

ãģĵãĤĵãģ«ãģ¡ãģ¯

-0.14

 vers

-0.14

spb

-0.14

$"

-0.14

-0.13

ityEngine

-0.13

sti

-0.13

har

-0.13

POSITIVE LOGITS

chnitt

0.15

assin

0.15

 Garrett

0.15

ddit

0.15

Ð²ÐµÐ´

0.15

wdx

0.15

elier

0.14

 Helmet

0.14

à¥įà¤¤à¤µ

0.14

 ÄĮech

0.14

Activations Density 0.007%

references to military corps, particularly the Marine Corps

No Comments

No Known Activations