INDEX

Explanations

references to administration or organizational entities

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

ongan

-0.18

jong

-0.15

ãģ¡ãģ¯

-0.15

emer

-0.14

CLUDING

-0.14

esta

-0.14

icrous

-0.14

.tar

-0.14

Readable

-0.14

.pdf

-0.13

POSITIVE LOGITS

 Admin

0.32

 staff

0.31

admin

0.31

 Staff

0.31

 admin

0.30

Admin

0.29

_admin

0.27

staff

0.26

_Admin

0.25

-admin

0.24

Activations Density 0.046%

references to administration or organizational entities

No Comments

No Known Activations