INDEX

Explanations

phrases indicating the presence or existence of features or amenities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãĥ³ãĤ¯

-0.15

 Infer

-0.14

oty

-0.14

 Ð·Ð°ÐºÐ»Ð°Ð´

-0.14

estate

-0.14

acie

-0.13

imo

-0.13

ãĥŃãĥ¼

-0.13

 Cass

-0.13

POSITIVE LOGITS

 also

0.16

0.15

no

0.14

 Ð¿ÑĢÐ°Ð²Ð´Ð°

0.14

anson

0.13

 Gibbs

0.13

iglia

0.13

à¥ĩà¤¦

0.13

 ServiceException

0.13

uess

0.13

Activations Density 0.062%

phrases indicating the presence or existence of features or amenities

No Comments

No Known Activations