INDEX

Explanations

titles and roles that indicate recognition or authority in academic or professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

angkan

-0.16

Contain

-0.16

leur

-0.15

ypy

-0.15

íĦ

-0.15

 lÃ´ng

-0.15

 iddi

-0.15

acher

-0.14

ostel

-0.14

Î»Ïİ

-0.14

POSITIVE LOGITS

0.15

 occasional

0.15

 status

0.14

 material

0.14

foe

0.14

Sc

0.14

 room

0.14

 continued

0.14

Activations Density 0.037%

titles and roles that indicate recognition or authority in academic or professional contexts

No Comments

No Known Activations