INDEX

Explanations

references to educational events and hands-on learning experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

.sharedInstance

-0.18

alnÄ±z

-0.16

anian

-0.15

nech

-0.15

lacak

-0.15

Äįin

-0.14

coverage

-0.14

oha

-0.14

ignet

-0.14

opis

-0.14

POSITIVE LOGITS

 hands

0.20

sim

0.16

 Hands

0.16

hands

0.15

 interact

0.15

 pressing

0.15

 simulated

0.15

 experiencing

0.15

 authentic

0.15

Î²Îµ

0.14

Activations Density 0.088%

references to educational events and hands-on learning experiences

No Comments

No Known Activations