INDEX

Explanations

possessive pronouns and references to personal relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Deaths

-0.18

 noses

-0.17

cÃŃ

-0.16

 Bodies

-0.15

 yourselves

-0.15

afx

-0.15

olla

-0.15

yms

-0.15

 careers

-0.15

 selves

-0.14

POSITIVE LOGITS

 story

0.24

 condition

0.21

 situation

0.21

 whereabouts

0.20

 movements

0.20

 plight

0.20

 predic

0.20

 name

0.19

 attackers

0.18

 rights

0.18

Activations Density 0.325%

possessive pronouns and references to personal relationships

No Comments

No Known Activations