INDEX

Explanations

references to specific items or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

inski

-0.17

/xhtml

-0.16

igg

-0.16

-0.14

inÃ§

-0.14

ollar

-0.14

anÃ¡

-0.14

OLF

-0.14

firm

-0.14

æīĭãĤĴ

-0.14

POSITIVE LOGITS

 Dexter

0.15

 Osman

0.15

uary

0.15

EventListener

0.14

/her

0.14

activate

0.14

ly

0.14

à¤Ŀ

0.14

pcs

0.14

errat

0.14

Activations Density 0.007%

references to specific items or entities

No Comments

No Known Activations