INDEX

Explanations

phrases related to product offerings and characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

arrings

-0.15

scene

-0.15

 scene

-0.15

wich

-0.15

opens

-0.14

elp

-0.14

bil

-0.14

ÑĸÐ¶

-0.14

EDI

-0.14

Bil

-0.13

POSITIVE LOGITS

ilden

0.16

iola

0.16

á»Ľ

0.16

bev

0.15

bang

0.15

chester

0.15

ļ

0.15

.removeListener

0.14

Conv

0.14

 îł

0.14

Activations Density 0.001%

phrases related to product offerings and characteristics

No Comments

No Known Activations