INDEX

Explanations

phrases related to choices and decision-making

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

uzey

-0.15

LOS

-0.14

 DAMAGE

-0.13

ÑĢÐ°Ð¶Ð´

-0.13

 slated

-0.13

 NEGLIGENCE

-0.13

_pins

-0.13

ìĿ´ìŀĲ

-0.13

 Battles

-0.13

ov

-0.13

POSITIVE LOGITS

 depending

0.19

 alike

0.18

depending

0.17

 respectively

0.17

Hue

0.15

-Ð¹

0.14

elsen

0.14

ep

0.14

orWhere

0.14

âķĹ

0.14

Activations Density 0.364%

phrases related to choices and decision-making

No Comments

No Known Activations