INDEX

Explanations

terms related to elevators and lifts

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

overe

-0.16

_TestCase

-0.14

ØªØ§

-0.14

tach

-0.14

aul

-0.14

orary

-0.14

UNG

-0.13

ÑĩÐµÑĤ

-0.13

ucc

-0.13

æ¡Į

-0.13

POSITIVE LOGITS

urse

0.15

ardy

0.15

olk

0.15

odont

0.14

yg

0.14

Hu

0.14

arte

0.13

ëł¹

0.13

fel

0.13

Ã¡r

0.13

Activations Density 0.007%

terms related to elevators and lifts

No Comments

No Known Activations