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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

logan

-0.17

anio

-0.17

iew

-0.17

orio

-0.15

.stat

-0.14

jam

-0.14

essen

-0.14

 Emer

-0.14

pread

-0.14

alog

-0.14

POSITIVE LOGITS

ìĦ±

0.15

RL

0.15

ivent

0.15

ÏĥÎ¯Î±

0.15

 cadre

0.14

Å¡nÃŃ

0.14

daemon

0.14

Zuk

0.14

alette

0.14

 Propel

0.14

Activations Density 0.058%

expressions of gratitude and appreciation

No Comments

No Known Activations