INDEX

Explanations

abbreviations or acronyms related to specific organizations or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

umbn

-0.18

Ã£o

-0.15

UCKET

-0.15

entai

-0.14

Evaluator

-0.14

-song

-0.14

ystem

-0.13

form

-0.13

omore

-0.13

apk

-0.13

POSITIVE LOGITS

sWith

0.15

esus

0.14

ÙĪØŃ

0.14

spo

0.14

-thumbnails

0.13

ROLE

0.13

ntag

0.13

Ùĳ

0.13

 Sullivan

0.13

/runtime

0.13

Activations Density 0.609%

abbreviations or acronyms related to specific organizations or concepts

No Comments

No Known Activations