INDEX

Explanations

occurrences of the word "use" and its variations related to functionality or application

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ships

-0.19

ross

-0.16

raz

-0.16

ree

-0.16

../../../

-0.16

toi

-0.15

.nz

-0.15

acey

-0.15

ship

-0.15

ore

-0.15

POSITIVE LOGITS

fully

0.22

full

0.18

ful

0.16

-bodied

0.15

ëŁī

0.15

lessly

0.15

FUL

0.15

fulness

0.14

éĢĶ

0.14

Activations Density 0.125%

occurrences of the word "use" and its variations related to functionality or application

No Comments

No Known Activations