INDEX

Explanations

variations of the word "til" and its usage in contexts related to time or conditions

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

imei

-0.17

acht

-0.16

obi

-0.16

ello

-0.16

elli

-0.16

LAR

-0.14

æ´¾

-0.14

ambi

-0.14

Ã©al

-0.14

ÑģÑĤÐ¸

-0.14

POSITIVE LOGITS

apia

0.20

ahun

0.19

 lá»ĩ

0.16

ting

0.16

·

0.16

-death

0.15

ley

0.15

tit

0.15

ney

0.15

ted

0.14

Activations Density 0.036%

variations of the word "til" and its usage in contexts related to time or conditions

No Comments

No Known Activations