INDEX

Explanations

proper nouns, specifically names of people and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ichten

-0.18

utsch

-0.17

ichte

-0.16

uien

-0.16

/stdc

-0.16

 Larson

-0.16

baugh

-0.16

 Minor

-0.16

utschein

-0.15

sembly

-0.15

POSITIVE LOGITS

 Pickup

0.21

 Cousins

0.20

 Knights

0.20

 Parkinson

0.20

 Tribe

0.20

 Hague

0.19

 Waist

0.19

 Doch

0.18

 Snape

0.18

 Souls

0.18

Activations Density 0.211%

proper nouns, specifically names of people and organizations

No Comments

No Known Activations