INDEX

Explanations

action-oriented words and activities involving animals or competitive situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

omik

-0.16

ichel

-0.15

ispers

-0.15

erti

-0.14

orn

-0.14

enville

-0.14

baugh

-0.14

ago

-0.14

=post

-0.14

 Alto

-0.13

POSITIVE LOGITS

 intense

0.31

 active

0.29

 intens

0.28

 intensity

0.28

 actively

0.28

 Active

0.27

fur

0.27

 intensive

0.27

Active

0.26

active

0.26

Activations Density 0.396%

action-oriented words and activities involving animals or competitive situations

No Comments

No Known Activations