INDEX

Explanations

variations of the word "use" and its related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

raid

-0.17

amt

-0.16

acades

-0.15

ãĥŃãĥ³

-0.15

à¸£

-0.15

zilla

-0.14

aurus

-0.14

actories

-0.14

rÃ¡

-0.14

onto

-0.14

POSITIVE LOGITS

fully

0.28

full

0.19

itarian

0.18

ful

0.18

 caution

0.18

lessly

0.17

ARCH

0.16

åĪ°çļĦ

0.16

fulness

0.16

Activations Density 0.148%

variations of the word "use" and its related forms

No Comments

No Known Activations