INDEX

Explanations

references to various awards and accolades in relation to individuals or works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ominator

-0.16

arsi

-0.15

riba

-0.15

ku

-0.14

.Enums

-0.14

itrust

-0.14

oller

-0.14

iedo

-0.14

ãĥĢãĥ¼

-0.14

asks

-0.13

POSITIVE LOGITS

stdafx

0.14

 coch

0.14

 unto

0.14

reb

0.14

chet

0.14

ithe

0.14

ÈĻ

0.14

edla

0.14

¦

0.14

Brief

0.13

Activations Density 0.023%

references to various awards and accolades in relation to individuals or works

No Comments

No Known Activations