INDEX

Explanations

titles of notable films and artistic works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

lemetry

-0.15

/Dk

-0.14

eczy

-0.14

ction

-0.14

ctime

-0.14

qli

-0.13

dle

-0.13

cks

-0.13

’ÑıÑĤ

-0.13

èĬ¸

-0.13

POSITIVE LOGITS

adays

0.23

odore

0.20

atre

0.18

atomy

0.18

mare

0.17

allo

0.16

linear

0.14

noon

0.14

âĢį

0.14

west

0.14

Activations Density 0.388%

titles of notable films and artistic works

No Comments

No Known Activations