INDEX

Explanations

terms related to occupancy and space

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ckt

-0.19

ï¸ı

-0.16

hem

-0.16

Ø·ÙĦ

-0.15

fbe

-0.14

 Ð½Ð°Ð»

-0.14

 Lana

-0.14

cket

-0.14

 reinc

-0.14

hem

-0.13

POSITIVE LOGITS

orsk

0.15

usted

0.15

ocol

0.14

à¸Ĩ

0.14

-NLS

0.14

 Nose

0.14

Î»Î¿Ïį

0.14

warm

0.14

adel

0.14

ment

0.13

Activations Density 0.019%

terms related to occupancy and space

No Comments

No Known Activations