INDEX

Explanations

details related to the layout and features of a house or property

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

//{{

-0.17

 tabletop

-0.16

ãģłãĤĪ

-0.16

 substance

-0.15

ittle

-0.15

 Grill

-0.15

esses

-0.14

ovah

-0.14

 Substance

-0.14

ï»¿#

-0.14

POSITIVE LOGITS

 bedroom

0.17

atak

0.17

errupted

0.15

axon

0.15

Ã±o

0.15

ux

0.15

urance

0.15

 bath

0.14

 bedrooms

0.14

/lg

0.14

Activations Density 0.025%

details related to the layout and features of a house or property

No Comments

No Known Activations