INDEX

Explanations

instances of the word "set" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 bÃ¶yle

-0.23

 ÚĨÙĨÛĮÙĨ

-0.16

SELF

-0.15

 ÑĤÐ°ÐºÐ¸Ð¹

-0.15

ATUS

-0.15

ê³¼ìĿĺ

-0.15

ä¼łå¥ĩ

-0.14

Uvs

-0.14

 buna

-0.14

 bunun

-0.14

POSITIVE LOGITS

th

0.30

thi

0.25

 This

0.22

tb

0.21

This

0.18

TH

0.18

 thee

0.17

-th

0.17

 those

0.17

_th

0.16

Activations Density 0.123%

instances of the word "set" in various contexts

No Comments

No Known Activations