INDEX

Explanations

proper names and titles related to individuals

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

olit

-0.19

zell

-0.17

ayment

-0.16

æŁĦ

-0.14

inez

-0.14

dar

-0.13

Regression

-0.13

sat

-0.13

 grand

-0.13

imen

-0.13

POSITIVE LOGITS

umer

0.17

åĮĸ

0.16

Kro

0.15

ubl

0.14

 boxed

0.14

 Verified

0.13

itto

0.13

viar

0.13

Activations Density 0.006%

proper names and titles related to individuals

No Comments

No Known Activations