INDEX

Explanations

references to patents and related intellectual property concepts

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

okie

-0.16

ftar

-0.15

inue

-0.14

æ¹¾

-0.14

ventario

-0.14

 Grat

-0.14

ATRIX

-0.13

 Nisan

-0.13

irÃ¡

-0.13

elm

-0.13

POSITIVE LOGITS

éģ

0.16

oppable

0.15

ahl

0.15

raid

0.14

 Fallon

0.14

amber

0.14

IGHL

0.14

oney

0.13

ree

0.13

outh

0.13

Activations Density 0.004%

references to patents and related intellectual property concepts

No Comments

No Known Activations