INDEX

Explanations

terms related to numerical data or specific years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

::__

-0.14

erra

-0.14

 smile

-0.14

 ãĥĶ

-0.14

à§

-0.14

Da

-0.14

acy

-0.13

 Bout

-0.13

zc

-0.13

ç¯ī

-0.13

POSITIVE LOGITS

 Ð¿ÐµÑĢÐµÐ»

0.15

 Martins

0.15

ilenames

0.15

edir

0.14

Ø§Ø¹ÙĬ

0.14

Ð·Ñĥ

0.14

UIScreen

0.13

aits

0.13

ildiÄŁi

0.13

isson

0.13

Activations Density 0.084%

terms related to numerical data or specific years

No Comments

No Known Activations