INDEX

Explanations

terms related to emotional techniques and various permissions in code

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

cke

-0.18

jom

-0.15

 rank

-0.15

 ä¸ĸ

-0.14

oles

-0.14

ramids

-0.14

annie

-0.14

çıŃ

-0.14

ILLE

-0.14

 preparation

-0.14

POSITIVE LOGITS

isi

0.17

apor

0.15

iske

0.15

lac

0.15

ĥ½

0.15

orial

0.14

umen

0.14

chez

0.14

emat

0.14

Activations Density 0.004%

terms related to emotional techniques and various permissions in code

No Comments

No Known Activations