INDEX

Explanations

expressions indicating product quality and production methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Beer

-0.20

Beer

-0.17

 Brewer

-0.17

 beer

-0.16

 Scoped

-0.15

Bud

-0.15

 Brew

-0.15

brew

-0.15

 Brewery

-0.15

ãĥĥãĥĪ

-0.14

POSITIVE LOGITS

rum

0.39

Rum

0.33

rum

0.32

 aged

0.26

Ron

0.25

mol

0.23

 Hait

0.23

 aÃ±

0.22

agr

0.22

 Jama

0.22

Activations Density 0.015%

expressions indicating product quality and production methods

No Comments

No Known Activations