INDEX

Explanations

instances of requests or suggestions for items to bring to events or classes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

anger

-0.19

iene

-0.17

kenin

-0.16

-0.15

gt

-0.15

theid

-0.15

rist

-0.15

odos

-0.15

 serg

-0.15

FieldValue

-0.14

POSITIVE LOGITS

ä¾Ľ

0.18

implicit

0.15

çħ¤

0.14

eros

0.14

lub

0.14

Supply

0.14

 ÙħØ«

0.14

VICES

0.14

Ð¸ÐºÑĥ

0.13

 supply

0.13

Activations Density 0.033%

instances of requests or suggestions for items to bring to events or classes

No Comments

No Known Activations