INDEX

Explanations

phrases that question reality or seek clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ð¶ÐµÐ½

-0.17

oux

-0.15

ouv

-0.15

iveau

-0.15

PELL

-0.15

Ð±Ð¾ÑĤ

-0.15

alfa

-0.15

llib

-0.15

ERSIST

-0.14

erialize

-0.14

POSITIVE LOGITS

Ä±ÅŁÄ±k

0.15

we

0.14

fat

0.13

-ÑĤÐ¾

0.13

SetName

0.13

artial

0.13

_exchange

0.13

 fucking

0.13

sÄ±z

0.13

 eject

0.13

Activations Density 0.037%

phrases that question reality or seek clarification

No Comments

No Known Activations