INDEX

Explanations

attributes and characteristics of objects 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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

efe

-0.15

iles

-0.14

rych

-0.14

 Jacobs

-0.13

 Miles

-0.13

udu

-0.13

ilename

-0.13

à¸¤

-0.13

agrams

-0.13

 getActivity

-0.13

POSITIVE LOGITS

vÄĽt

0.17

PSA

0.15

assen

0.15

ustin

0.15

SCI

0.15

.Formatter

0.14

ã

0.14

_{}

0.14

ÅĽÄĩ

0.14

Ð¾Ð»Ñİ

0.14

Activations Density 0.236%

attributes and characteristics of objects or entities

No Comments

No Known Activations