INDEX

Explanations

references to specific positions or instances in time or sequence

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

continued

-0.19

lie

-0.17

 continued

-0.16

rie

-0.16

 Continued

-0.15

fal

-0.15

ylko

-0.15

cont

-0.14

unker

-0.14

POSITIVE LOGITS

 former

0.25

 first

0.22

former

0.20

 primero

0.20

ç¬¬ä¸Ģ

0.17

 Former

0.17

uada

0.17

Former

0.17

 ì²«

0.16

.first

0.16

Activations Density 0.051%

references to specific positions or instances in time or sequence

No Comments

No Known Activations