INDEX

Explanations

references to simulations and modeling processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 taken

-0.15

lessness

-0.15

itere

-0.15

istrovstvÃŃ

-0.14

eron

-0.14

è´

-0.14

cher

-0.14

 Evangel

-0.13

.selenium

-0.13

marsh

-0.13

POSITIVE LOGITS

IRROR

0.18

ERCHANT

0.16

ias

0.16

ument

0.16

posium

0.16

oeff

0.15

onds

0.14

Gum

0.14

andatory

0.14

colo

0.14

Activations Density 0.017%

references to simulations and modeling processes

No Comments

No Known Activations