INDEX

Explanations

phrases indicating connections or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

GenerationStrategy

-0.16

 Ú©ÙĨØ§Ø±

-0.13

ofday

-0.13

ansi

-0.13

marvin

-0.13

abay

-0.13

rack

-0.13

kÄ±r

-0.13

latlong

-0.12

emiz

-0.12

POSITIVE LOGITS

Dit

0.16

 similarly

0.16

 ÙĩÙħÚĨÙĨÛĮÙĨ

0.15

ear

0.15

 takÃ©

0.15

dit

0.15

CALE

0.14

Similarly

0.14

ÃŁerdem

0.14

lick

0.14

Activations Density 0.315%

phrases indicating connections or relationships

No Comments

No Known Activations

phrases indicating connections or relationships

No Comments

No Known Activations