INDEX

Explanations

phrases indicating pricing or cost-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

.decorate

-0.16

illion

-0.16

crollView

-0.14

edException

-0.14

isu

-0.14

oids

-0.14

raq

-0.14

earn

-0.13

endor

-0.13

ãĥ³ãĥĩãĤ£

-0.13

POSITIVE LOGITS

 less

0.26

 only

0.25

 penn

0.25

 dirt

0.23

 Less

0.21

 fractions

0.21

 just

0.21

only

0.21

 mere

0.21

 fraction

0.20

Activations Density 0.065%

phrases indicating pricing or cost-related information

No Comments

No Known Activations