INDEX

Explanations

references to the authorship or credit of works and content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

aby

-0.16

ampa

-0.15

arks

-0.14

uard

-0.14

bound

-0.14

actor

-0.14

Ã©v

-0.14

XC

-0.13

lect

-0.13

ogle

-0.13

POSITIVE LOGITS

 admin

0.38

 Admin

0.31

Admin

0.31

 Administrator

0.30

admin

0.30

 administrator

0.28

_admin

0.28

Administrator

0.27

_ADMIN

0.27

ADMIN

0.26

Activations Density 0.029%

references to the authorship or credit of works and content

No Comments

No Known Activations