INDEX

Explanations

terms and concepts related to mathematical modeling and organizational research

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

sted

-0.16

eza

-0.15

enth

-0.15

iaux

-0.14

uet

-0.14

nothrow

-0.14

ighth

-0.14

lian

-0.14

ilent

-0.14

fits

-0.13

POSITIVE LOGITS

EG

0.18

 Baum

0.16

ÐµÑĢÐ¸Ð½Ð°

0.14

chor

0.13

essen

0.13

 Mech

0.13

ØªÙĩ

0.13

hq

0.13

patrick

0.13

]={↵

0.13

Activations Density 0.380%

terms and concepts related to mathematical modeling and organizational research

No Comments

No Known Activations