INDEX

Explanations

complex interrelationships among various components in a system

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ickest

-0.15

ãģĵãģĨ

-0.15

Ð½Ð¾Ð´

-0.14

ensch

-0.14

orm

-0.14

 ÑĦÐµÑĢ

-0.14

iska

-0.14

çĽ¤

-0.14

 çı

-0.14

ivor

-0.14

POSITIVE LOGITS

owski

0.17

0.15

aug

0.15

ë¥

0.15

.har

0.14

 analog

0.14

 grace

0.14

 classic

0.13

.BackgroundImage

0.13

asics

0.13

Activations Density 0.251%

complex interrelationships among various components in a system

No Comments

No Known Activations