INDEX

Explanations

instances of the word "embrace" and its variations, indicating a focus on acceptance and inclusion

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

hone

-0.16

hq

-0.16

ÐµÐ´Ð¶

-0.15

ries

-0.15

Ð½ÐºÐ¸

-0.15

oodoo

-0.14

isay

-0.14

prech

-0.14

ials

-0.14

ease

-0.14

POSITIVE LOGITS

hold

0.20

Ø§Ø¹Øª

0.17

 hold

0.16

bers

0.15

bing

0.15

bling

0.15

)((((

0.15

fast

0.15

ful

0.14

Activations Density 0.049%

instances of the word "embrace" and its variations, indicating a focus on acceptance and inclusion

No Comments

No Known Activations