INDEX

Explanations

metrics and parameters related to data analysis

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

Ã©gor

-0.18

imir

-0.17

enou

-0.16

Sharper

-0.15

inic

-0.14

gia

-0.14

HCI

-0.14

 respir

-0.14

okud

-0.14

.struts

-0.13

POSITIVE LOGITS

elaide

0.15

eland

0.14

jed

0.14

fon

0.14

ixel

0.14

 Howell

0.14

izz

0.14

 loose

0.13

Activations Density 0.364%

metrics and parameters related to data analysis

No Comments

No Known Activations