INDEX

Explanations

words related to habits and behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ea

-0.16

å¶

-0.15

isch

-0.15

jom

-0.15

ei

-0.14

uyÃªn

-0.14

olest

-0.14

hong

-0.14

oria

-0.14

quel

-0.14

POSITIVE LOGITS

uated

0.19

ually

0.19

imeo

0.18

 Habit

0.17

 habit

0.17

habit

0.17

akk

0.17

uby

0.16

ta

0.15

actics

0.15

Activations Density 0.021%

words related to habits and behaviors

No Comments

No Known Activations