INDEX

Explanations

descriptions of people and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

meno

-0.15

isku

-0.15

VML

-0.14

alm

-0.14

aho

-0.14

 multiple

-0.14

ARGV

-0.14

å¹¹

-0.13

ToBounds

-0.13

ifi

-0.13

POSITIVE LOGITS

etim

0.15

abelle

0.15

eam

0.14

chia

0.14

 Horton

0.13

à¥įà¤ªà¤°

0.13

á»§i

0.13

 lÃ´ng

0.13

Ð¾ÐºÑģÐ¸

0.13

_RTC

0.13

Activations Density 0.277%

descriptions of people and their attributes

No Comments

No Known Activations