INDEX

Explanations

references to data structures or mathematical variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ItemSelectedListener

-0.16

asco

-0.15

.ActionListener

-0.15

iri

-0.14

 ä¹Ŀ

-0.13

aira

-0.13

izza

-0.13

inci

-0.13

 roma

-0.13

Ø®Ø§ÙĨÙĩ

-0.13

POSITIVE LOGITS

sm

0.17

bra

0.15

okrat

0.15

ypes

0.14

 fiat

0.14

oblin

0.14

fld

0.13

ovna

0.13

 Lightning

0.13

 Thornton

0.13

Activations Density 0.005%

references to data structures or mathematical variables

No Comments

No Known Activations