INDEX

Explanations

references to scientific publications and data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ilet

-0.16

wo

-0.15

 Nolan

-0.15

 industry

-0.14

orda

-0.14

kaar

-0.14

Voy

-0.14

 ******************************************************************************↵

-0.13

avy

-0.13

qus

-0.13

POSITIVE LOGITS

ndon

0.18

æĴ

0.15

arsity

0.14

mÃŃt

0.14

ropical

0.14

iations

0.14

ublic

0.14

ucz

0.14

çĶŁ

0.13

 Municipal

0.13

Activations Density 0.028%

references to scientific publications and data

No Comments

No Known Activations

references to scientific publications and data

No Comments

No Known Activations