INDEX

Explanations

terms associated with contrast or comparison, particularly in contexts involving conditions or traits

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

ouz

-0.21

 ÑĥÐ¿

-0.17

ulur

-0.16

PTY

-0.15

steder

-0.15

afa

-0.14

clip

-0.14

onn

-0.14

alker

-0.14

Motion

-0.14

POSITIVE LOGITS

 notwithstanding

0.23

 aside

0.23

 otherwise

0.21

 included

0.20

 Otherwise

0.18

otherwise

0.16

aer

0.15

-wise

0.15

included

0.15

 Included

0.14

Activations Density 0.117%

terms associated with contrast or comparison, particularly in contexts involving conditions or traits

No Comments

No Known Activations