INDEX

Explanations

references to patented products and technologies

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

PLEX

-0.16

inox

-0.15

ipi

-0.14

aversal

-0.14

uers

-0.14

rÅ¯

-0.14

atoria

-0.14

bÄĽ

-0.14

inki

-0.14

RenderingContext

-0.14

POSITIVE LOGITS

 technology

0.18

technology

0.18

 feature

0.18

 bindActionCreators

0.16

nost

0.15

 engine

0.14

 Twist

0.14

 system

0.14

 patented

0.14

.datasource

0.14

Activations Density 0.085%

references to patented products and technologies

No Comments

No Known Activations