INDEX

Explanations

the word "much" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

nable

-0.17

icut

-0.16

eer

-0.15

ActionCreators

-0.15

ourg

-0.14

icap

-0.14

ein

-0.14

 McCart

-0.14

.readString

-0.14

à¸§à¸¥

-0.14

POSITIVE LOGITS

º

0.15

PRIVATE

0.15

ux

0.15

hom

0.15

mah

0.14

 polarity

0.14

awah

0.14

ala

0.13

 remainder

0.13

Apt

0.13

Activations Density 0.021%

the word "much" and its variations in different contexts

No Comments

No Known Activations