INDEX

Explanations

key technical terms and numerical indicators related to research or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ÑĢÐ³

-0.15

jam

-0.14

 Ø³Ø±

-0.14

 charge

-0.14

aco

-0.14

anni

-0.14

rets

-0.14

ersed

-0.14

Tre

-0.13

re

-0.13

POSITIVE LOGITS

ovny

0.18

ropa

0.15

anza

0.15

odian

0.14

udden

0.14

ORTH

0.14

 Kare

0.14

æĽ

0.14

Ð¾Ð»Ð½Ð¸ÑĤÐµÐ»ÑĮ

0.14

mlin

0.14

Activations Density 0.001%

key technical terms and numerical indicators related to research or documentation

No Comments

No Known Activations