INDEX

Explanations

documentation summaries or descriptions related to code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ÑģÐ»ÐµÐ´

-0.14

 Cald

-0.14

èª

-0.14

ÙĦÛĮÙĦ

-0.14

aps

-0.14

iki

-0.13

serviceName

-0.13

sec

-0.13

è¸

-0.13

ole

-0.13

POSITIVE LOGITS

.metamodel

0.15

DISABLE

0.14

-ÑĤÐ¾

0.14

vero

0.14

ativas

0.13

piler

0.13

enas

0.13

uyá»ĩt

0.13

Activations Density 0.001%

documentation summaries or descriptions related to code

No Comments

No Known Activations