INDEX

Explanations

references to educational programs and workshops

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

irit

-0.15

angu

-0.15

anni

-0.14

enco

-0.14

stantiate

-0.14

erken

-0.14

anggan

-0.14

lÃ¡

-0.14

egie

-0.14

 bist

-0.14

POSITIVE LOGITS

 offered

0.35

 taught

0.31

 held

0.25

 Offer

0.25

 teaches

0.23

held

0.22

run

0.22

 teaching

0.22

 conducted

0.21

Offer

0.20

Activations Density 0.177%

references to educational programs and workshops

No Comments

No Known Activations