INDEX

Explanations

variations and mentions of the word "sesame."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

tdown

-0.18

apos

-0.14

 waking

-0.14

Ø±Ø¬

-0.14

 Bren

-0.14

orst

-0.13

 shipping

-0.13

ë§ī

-0.13

ÐµÑģÐ¿

-0.13

igos

-0.13

POSITIVE LOGITS

uai

0.20

AME

0.17

enta

0.16

 accompanying

0.15

YPRE

0.15

amework

0.15

pread

0.14

å¼¥

0.14

æ£ļ

0.14

è¹

0.14

Activations Density 0.005%

variations and mentions of the word "sesame."

No Comments

No Known Activations