INDEX

Explanations

words that express simplicity or lack of complexity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 âĹĦ

-0.17

Ãłng

-0.16

erna

-0.15

imized

-0.15

aland

-0.14

pack

-0.14

 Karlov

-0.14

ropic

-0.14

ulfilled

-0.13

POSITIVE LOGITS

Ĥæķ°

0.17

icontrol

0.15

ê°Ħ

0.14

åŃ¤

0.14

ochen

0.13

ltra

0.13

ites

0.13

ToDate

0.13

uguay

0.13

ÐºÑĢÐ°ÑĹ

0.13

Activations Density 0.070%

words that express simplicity or lack of complexity

No Comments

No Known Activations