INDEX

Explanations

phrases that indicate varying degrees of quality or standards

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

ew

-0.17

ed

-0.16

du

-0.16

unas

-0.15

Ø§

-0.15

ess

-0.15

ft

-0.15

elves

-0.15

Ð¾ÐºÑĢÐ°ÑĤÐ¸

-0.14

edd

-0.14

POSITIVE LOGITS

led

0.46

åĪ«

0.30

headed

0.28

åĪ¥

0.28

(Level

0.23

-headed

0.22

ution

0.20

LED

0.17

ings

0.17

/type

0.17

Activations Density 0.041%

phrases that indicate varying degrees of quality or standards

No Comments

No Known Activations