INDEX

Explanations

first-person pronouns and phrases indicating personal perspective or opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 breakdown

-0.14

è²Ŀ

-0.14

 legit

-0.14

Î¯Î³

-0.14

ipur

-0.14

 sworn

-0.13

imity

-0.13

Util

-0.13

ihat

-0.13

Ã±as

-0.13

POSITIVE LOGITS

 shall

0.24

 hast

0.24

 confess

0.21

da

0.20

 note

0.19

 incl

0.19

 reproduce

0.18

 accordingly

0.18

pres

0.17

 presum

0.17

Activations Density 0.271%

first-person pronouns and phrases indicating personal perspective or opinion

No Comments

No Known Activations