INDEX

Explanations

expressions related to bravery and courage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

lue

-0.16

acro

-0.15

ãĥĨãĥ«

-0.14

ÐµÐ½Ð·

-0.14

vore

-0.14

tega

-0.14

 ponder

-0.14

loub

-0.14

avana

-0.14

lis

-0.13

POSITIVE LOGITS

ously

0.21

 courage

0.18

bold

0.17

-bold

0.16

ous

0.16

æķ¢

0.15

 courageous

0.15

 bold

0.15

fires

0.14

lessly

0.14

Activations Density 0.031%

expressions related to bravery and courage

No Comments

No Known Activations