INDEX

Explanations

expressions that indicate practicality or functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

edb

-0.21

edBy

-0.19

ed

-0.18

anian

-0.17

edn

-0.16

iah

-0.16

rov

-0.16

kker

-0.15

eday

-0.15

alla

-0.15

POSITIVE LOGITS

ness

0.42

lest

0.35

NESS

0.31

mente

0.28

0.27

nes

0.26

/help

0.23

/use

0.21

-looking

0.21

 tool

0.20

Activations Density 0.104%

expressions that indicate practicality or functionality

No Comments

No Known Activations