INDEX

Explanations

references to individuals' actions and emotional states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ile

-0.17

awan

-0.15

kov

-0.14

.utilities

-0.14

ben

-0.14

ioxide

-0.14

antz

-0.14

 forks

-0.14

ìĭĿ

-0.13

 spect

-0.13

POSITIVE LOGITS

aler

0.16

ICODE

0.15

à¸´à¹ī

0.15

URT

0.15

Calibri

0.14

ouser

0.14

 GOODS

0.14

">ÃĹ</

0.14

ClientRect

0.14

elps

0.14

Activations Density 0.043%

references to individuals' actions and emotional states

No Comments

No Known Activations