INDEX

Explanations

references to achieving goals or capabilities

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

 ÑĤÐµÐº

-0.17

ToProps

-0.16

_consts

-0.15

StackNavigator

-0.15

 baÅŁÄ±na

-0.14

Ø¯Ø§Ø¯

-0.14

uyu

-0.14

ucha

-0.14

pie

-0.14

 Kong

-0.14

POSITIVE LOGITS

bis

0.15

Glo

0.15

Bis

0.14

 sing

0.14

 Benedict

0.14

ayet

0.14

ajor

0.14

Subview

0.14

undle

0.14

Activations Density 0.023%

references to achieving goals or capabilities

No Comments

No Known Activations