INDEX

Explanations

numerical or statistical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

rese

-0.15

ung

-0.15

rup

-0.15

ade

-0.15

Ade

-0.14

ucu

-0.14

YS

-0.14

ayo

-0.14

avo

-0.14

 Coast

-0.13

POSITIVE LOGITS

ylie

0.16

 Kron

0.15

GuidId

0.15

UNCT

0.14

ASCADE

0.14

Ø§Ø®ØªÛĮ

0.14

ControlEvents

0.14

apore

0.14

ãĤ½ãĥ³

0.14

gin

0.14

Activations Density 0.013%

numerical or statistical data

No Comments

No Known Activations