INDEX

Explanations

references to legal or regulatory terms and positions

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

 addCriterion

-0.17

yat

-0.17

ullet

-0.15

meld

-0.14

elog

-0.13

ColumnsMode

-0.13

 Barnett

-0.13

deen

-0.13

.Creator

-0.13

POSITIVE LOGITS

Ĥ¹

0.14

mobx

0.13

 indeed

0.13

 cert

0.13

 Lesser

0.12

ret

0.12

 qual

0.12

acades

0.12

 dipping

0.12

Activations Density 0.021%

references to legal or regulatory terms and positions

No Comments

No Known Activations