INDEX

Explanations

expressions of gratitude and appreciation

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

-0.18

yk

-0.16

 loving

-0.16

ayi

-0.15

aldo

-0.15

å¥³åŃĲ

-0.14

atte

-0.14

POSITIVE LOGITS

áº

0.15

Ð¼ÐµÑĤÑĮ

0.14

LOPT

0.14

.mixin

0.14

 Crest

0.14

Ì§

0.14

eÃ§

0.14

rÃ³

0.14

Ã«n

0.14

omon

0.13

Activations Density 0.105%

expressions of gratitude and appreciation

No Comments

No Known Activations