INDEX

Explanations

numerical ratings and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

azar

-0.15

Ŀi

-0.15

 contrary

-0.15

ender

-0.14

cente

-0.13

jin

-0.13

 CORE

-0.13

dem

-0.13

producer

-0.13

 Experts

-0.13

POSITIVE LOGITS

0.15

strup

0.14

lte

0.14

OperationException

0.14

ior

0.14

0.13

mol

0.13

oog

0.13

/high

0.13

wp

0.13

Activations Density 0.023%

numerical ratings and evaluations

No Comments

No Known Activations