INDEX

Explanations

references to various subscription models or services

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

-0.15

Aud

-0.15

aud

-0.15

 Freed

-0.14

enk

-0.14

istrovstvÃŃ

-0.14

NC

-0.14

ÅŁehir

-0.13

ITT

-0.13

 Seas

-0.13

POSITIVE LOGITS

IDEO

0.15

lica

0.15

matic

0.15

 NSStringFromClass

0.15

tes

0.15

aln

0.14

bsd

0.14

ssi

0.14

ypad

0.14

ãģ

0.14

Activations Density 0.002%

references to various subscription models or services

No Comments

No Known Activations