INDEX

Explanations

references to the term "dry" 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

atron

-0.15

Ø³ÙĬØ©

-0.15

alue

-0.15

à¸°

-0.14

iasi

-0.14

olem

-0.14

olib

-0.14

Extent

-0.14

ëĭ¹

-0.13

POSITIVE LOGITS

outs

0.23

out

0.22

sdale

0.22

wall

0.20

lands

0.18

dry

0.17

-out

0.17

 Lennon

0.17

dock

0.17

den

0.17

Activations Density 0.015%

references to the term "dry" in various contexts

No Comments

No Known Activations