INDEX

Explanations

references to handles or gripping mechanisms in tools or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

pher

-0.16

 standardUserDefaults

-0.15

nem

-0.15

.='

-0.14

Ø¨Ø§Ø¨

-0.14

aeper

-0.14

evi

-0.14

atica

-0.13

esser

-0.13

addock

-0.13

POSITIVE LOGITS

ISA

0.16

Ø±Ø§Ø¯

0.15

uenta

0.15

amura

0.14

less

0.14

erner

0.14

ile

0.14

asser

0.14

iode

0.14

iley

0.13

Activations Density 0.022%

references to handles or gripping mechanisms in tools or products

No Comments

No Known Activations