INDEX

Explanations

references to the concept of multiple entities or components

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

-0.17

ugh

-0.16

ucker

-0.15

ohn

-0.15

Ð»ÑıÐ²

-0.15

 Grim

-0.15

ORS

-0.14

ami

-0.14

nh

-0.14

oui

-0.14

POSITIVE LOGITS

ercial

0.16

etric

0.16

ythe

0.15

arend

0.15

Ãły

0.15

isinden

0.14

isoft

0.14

ãģĹãĤĩ

0.14

celed

0.14

raphics

0.14

Activations Density 0.283%

references to the concept of multiple entities or components

No Comments

No Known Activations