INDEX

Explanations

articles and references to new developments, technologies, and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

.Highlight

-0.14

ylland

-0.14

Æ¡n

-0.13

lify

-0.13

enheim

-0.13

ieri

-0.13

ãĥ¼ãĥĸ

-0.13

POSITIVE LOGITS

 called

0.20

called

0.18

åı«

0.17

-called

0.15

 Called

0.15

 technique

0.15

 procedure

0.14

landa

0.14

utton

0.14

sv

0.14

Activations Density 0.222%

articles and references to new developments, technologies, and methods

No Comments

No Known Activations