INDEX

Explanations

phrases indicating time and experience in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

oppel

-0.14

ÑģÐ»Ð¸

-0.14

lap

-0.14

 crunch

-0.14

 harek

-0.14

akk

-0.13

 WithEvents

-0.13

adu

-0.13

avn

-0.13

-Ðµ

-0.13

POSITIVE LOGITS

 small

0.27

pie

0.26

 individual

0.23

Pie

0.23

 various

0.21

 smaller

0.21

å°ı

0.21

small

0.20

Pie

0.20

 nhá»ı

0.20

Activations Density 0.233%

phrases indicating time and experience in context

No Comments

No Known Activations