INDEX

Explanations

references to economic institutions or principles

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

SingleOrDefault

-0.17

Å¥

-0.16

-0.15

 sque

-0.15

ÑĸÐ´Ð½Ð¾

-0.14

 Wich

-0.14

lac

-0.14

ÙĮ

-0.14

CHO

-0.14

POSITIVE LOGITS

 quantitative

0.28

 Quant

0.28

 stimulus

0.26

 stim

0.24

 Stim

0.24

stim

0.23

Quant

0.22

 stimuli

0.22

QE

0.22

QE

0.20

Activations Density 0.025%

references to economic institutions or principles

No Comments

No Known Activations