INDEX

Explanations

references to legal violations or breaches of conduct

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

æŀĿ

-0.15

ÑģÑĤÑİ

-0.15

imizer

-0.15

 Gale

-0.15

 Tall

-0.15

_subtype

-0.15

á»Ļc

-0.14

/ay

-0.14

iras

-0.14

 Allocator

-0.14

POSITIVE LOGITS

 manip

0.15

amam

0.15

 Manip

0.15

ĵn

0.15

 versa

0.14

ept

0.14

 manipulation

0.14

à¹ĩà¸Ķ

0.14

éĩ

0.14

Activations Density 0.043%

references to legal violations or breaches of conduct

No Comments

No Known Activations