INDEX

Explanations

terms related to physical dimensions and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

dol

-0.18

heet

-0.15

laz

-0.15

mars

-0.15

foot

-0.14

lap

-0.14

buz

-0.14

itesi

-0.14

etat

-0.14

åħ¥ãĤĬ

-0.14

POSITIVE LOGITS

wise

0.38

ening

0.33

ened

0.33

 wise

0.25

-wise

0.25

 Wise

0.20

eners

0.20

iest

0.20

wis

0.19

WISE

0.19

Activations Density 0.082%

terms related to physical dimensions and measurements

No Comments

No Known Activations