INDEX

Explanations

references to testing or challenges faced by individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

empor

-0.19

pNet

-0.18

eren

-0.17

Ø´Øª

-0.16

imers

-0.16

decess

-0.16

kÃ³w

-0.16

abol

-0.15

Ð²ÑĸÐ»ÑĮ

-0.15

atron

-0.15

POSITIVE LOGITS

Min

0.17

Min

0.16

Ð¸Ð½

0.15

/test

0.15

pose

0.15

MIN

0.14

ç¢

0.14

link

0.14

ashi

0.14

 Lesser

0.14

Activations Density 0.046%

references to testing or challenges faced by individuals or entities

No Comments

No Known Activations