INDEX

Explanations

phrases related to convictions and transformative actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ÑĭÐ²

-0.16

affen

-0.15

ikel

-0.15

luv

-0.14

hoo

-0.14

xit

-0.14

ichel

-0.14

 Ð¿ÐµÑĢÐµÐ±

-0.14

ufen

-0.14

anst

-0.14

POSITIVE LOGITS

elo

0.18

elp

0.15

Kra

0.15

 Hipp

0.15

igue

0.15

éĥİ

0.14

ÐµÐ³

0.14

 Titles

0.14

agine

0.14

?q

0.14

Activations Density 0.001%

phrases related to convictions and transformative actions

No Comments

No Known Activations