INDEX

Explanations

terms related to exhibitions, history, and cultural artifacts

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

dpi

-0.15

leigh

-0.14

Ø¹ÙĬØ©

-0.14

Pur

-0.14

 ages

-0.14

éŀ

-0.13

 Patch

-0.13

getParam

-0.13

abyrinth

-0.13

GOR

-0.13

POSITIVE LOGITS

allet

0.15

Ø§Øª

0.14

Vir

0.14

 beden

0.14

é¡Į

0.14

æ¢°

0.14

cra

0.14

hog

0.14

ecz

0.14

rÃ³d

0.14

Activations Density 1.500%

terms related to exhibitions, history, and cultural artifacts

No Comments

No Known Activations