INDEX

Explanations

references to the name "Montgomery."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 é¦¬

-0.15

.Magenta

-0.14

-backend

-0.14

sg

-0.13

quia

-0.13

IRD

-0.13

elez

-0.13

tun

-0.13

ieves

-0.13

éŀ

-0.13

POSITIVE LOGITS

shire

0.16

ucz

0.15

ilst

0.15

istrovstvÃŃ

0.15

arella

0.14

ewise

0.14

mere

0.14

tsy

0.14

ycastle

0.14

Activations Density 0.001%

references to the name "Montgomery."

No Comments

No Known Activations