INDEX

Explanations

names of notable personalities and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

venir

-0.15

_except

-0.14

uw

-0.14

 Ð³Ð¾Ð»Ð¾Ñģ

-0.14

 thÆ°á»Łng

-0.14

alance

-0.14

Ã¼nd

-0.13

 à¹Ĩ

-0.13

Touches

-0.13

à¸£à¸ĵ

-0.13

POSITIVE LOGITS

0.15

 Weaver

0.14

akov

0.14

oke

0.14

on

0.14

asio

0.14

sil

0.13

ACHE

0.13

and

0.13

 Gram

0.13

Activations Density 0.134%

names of notable personalities and places

No Comments

No Known Activations

names of notable personalities and places

No Comments

No Known Activations