INDEX

Explanations

references to personal data and privacy-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

_PCI

-0.16

Virgin

-0.14

MPI

-0.14

anim

-0.14

wc

-0.14

(DataType

-0.14

iers

-0.14

iffe

-0.14

zaw

-0.14

tron

-0.13

POSITIVE LOGITS

baugh

0.16

ãģ¡ãĤĥ

0.15

³

0.15

hausen

0.14

 FrantiÅ¡ek

0.14

ZN

0.14

Canonical

0.13

itar

0.13

Ã¶h

0.13

Activations Density 0.033%

references to personal data and privacy-related information

No Comments

No Known Activations