INDEX

Explanations

occurrences of the word "of"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

olumn

-0.15

lich

-0.14

ileo

-0.14

anova

-0.14

illion

-0.13

ac

-0.13

roz

-0.13

 Guth

-0.13

gorit

-0.13

owers

-0.13

POSITIVE LOGITS

few

0.20

 Europe

0.19

LETE

0.17

 America

0.16

Msp

0.15

ç½²

0.15

few

0.14

America

0.14

Few

0.14

Few

0.14

Activations Density 0.046%

occurrences of the word "of"

No Comments

No Known Activations