INDEX

Explanations

questions that begin with "Are"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-0.16

lore

-0.16

eur

-0.15

ills

-0.15

rzy

-0.15

orra

-0.15

pery

-0.14

ruc

-0.14

rÃ©

-0.14

poons

-0.14

POSITIVE LOGITS

zzo

0.25

ospace

0.25

nda

0.23

nds

0.22

ady

0.21

tha

0.20

obic

0.18

nts

0.18

psilon

0.18

tap

0.17

Activations Density 0.033%

questions that begin with "Are"

No Comments

No Known Activations