INDEX

Explanations

phrases related to boasting or showcasing achievements

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

halb

-0.15

ussen

-0.15

¾

-0.15

trap

-0.14

ukt

-0.14

vez

-0.14

ugg

-0.14

wil

-0.14

-0.13

 Ãºn

-0.13

POSITIVE LOGITS

-about

0.18

 about

0.18

 About

0.16

_about

0.15

 having

0.15

ably

0.15

.safe

0.15

ãĥªãĥ¼

0.15

About

0.14

antly

0.14

Activations Density 0.014%

phrases related to boasting or showcasing achievements

No Comments

No Known Activations