INDEX

Explanations

the word "just" in various contexts indicating proximity or specification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

VERS

-0.15

Ø¨ÛĮÙĨ

-0.15

plet

-0.15

orr

-0.14

 Nearby

-0.14

pon

-0.14

agedList

-0.14

oro

-0.14

ANCH

-0.14

 nearby

-0.13

POSITIVE LOGITS

 outside

0.24

outside

0.20

 steps

0.19

 beyond

0.19

 past

0.19

 feet

0.18

 weeks

0.18

 moments

0.17

 before

0.17

 minutes

0.17

Activations Density 0.036%

the word "just" in various contexts indicating proximity or specification

No Comments

No Known Activations