INDEX

Explanations

references to awards and accolades in academic or artistic contexts

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

zm

-0.15

 Conway

-0.14

ernet

-0.14

 Vermont

-0.13

Connect

-0.13

DataGridViewTextBoxColumn

-0.13

ÐµÐ»Ñİ

-0.13

 Cant

-0.13

angan

-0.13

inde

-0.13

POSITIVE LOGITS

æļ

0.17

kla

0.16

ioni

0.16

hei

0.15

 Miche

0.15

ipse

0.15

ei

0.15

leck

0.14

.weixin

0.14

 Shield

0.14

Activations Density 0.430%

references to awards and accolades in academic or artistic contexts

No Comments

No Known Activations