INDEX

Explanations

technical code or programming elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

adio

-0.17

/sites

-0.15

ãĤĴãģĭ

-0.15

 Volk

-0.15

 Provid

-0.15

 Ø§ÙĦÙĨÙĩ

-0.14

à¹ģà¸ľ

-0.14

remarks

-0.14

_tolerance

-0.14

 resourceName

-0.14

POSITIVE LOGITS

 room

0.22

pollo

0.21

 thread

0.21

 forum

0.20

 Room

0.20

 rooms

0.20

room

0.20

 latest

0.19

ago

0.19

 topic

0.19

Activations Density 0.028%

technical code or programming elements

No Comments

No Known Activations