INDEX

Explanations

instances of the word "was" and variations of the verb "to be" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Vill

-0.15

Ð°Ð»ÐµÐ¶

-0.15

cke

-0.14

ê¸ī

-0.14

DbType

-0.14

ensem

-0.14

orer

-0.14

ooter

-0.14

 penet

-0.14

-0.13

POSITIVE LOGITS

.CreateInstance

0.17

.omg

0.17

 visit

0.16

elop

0.15

nou

0.15

 drive

0.15

pets

0.15

acerb

0.14

ampo

0.14

ida

0.14

Activations Density 0.042%

instances of the word "was" and variations of the verb "to be" used in various contexts

No Comments

No Known Activations