INDEX

Explanations

references to personal pronouns and possessive relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ibar

-0.16

itamin

-0.15

EXPR

-0.15

Hashtable

-0.15

Ð»Ð¾Ð¿

-0.14

Ãªnh

-0.14

inant

-0.14

/UIKit

-0.14

Ã³st

-0.14

ipmap

-0.14

POSITIVE LOGITS

own

0.18

asse

0.16

ë¹Ľ

0.15

atha

0.14

omba

0.14

 Loved

0.14

rede

0.14

ÙĤÛĮ

0.14

 imagination

0.14

Ð°Ð·Ð°

0.14

Activations Density 0.371%

references to personal pronouns and possessive relationships

No Comments

No Known Activations