INDEX

Explanations

structured references to dates, events, and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ambi

-0.16

gb

-0.15

ickerView

-0.15

rita

-0.14

adu

-0.14

ags

-0.14

eydi

-0.13

}elseif

-0.13

agan

-0.13

illi

-0.13

POSITIVE LOGITS

0.14

tainment

0.13

inha

0.13

 masse

0.13

=~

0.13

ypi

0.13

azzi

0.13

å»¶

0.12

 Jury

0.12

cro

0.12

Activations Density 0.271%

structured references to dates, events, and actions

No Comments

No Known Activations