INDEX

Explanations

years and dates associated with events or changes in position

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

okol

-0.15

à¸´à¸Ļà¸Ĺà¸£

-0.14

yla

-0.14

æĮ

-0.14

ahan

-0.14

allest

-0.14

ãĥ¼ãĥ

-0.14

ëª¬

-0.14

tour

-0.14

atur

-0.13

POSITIVE LOGITS

Äł

0.14

anship

0.14

eneg

0.14

/copyleft

0.13

è±

0.13

Ware

0.13

fat

0.13

alarÄ±ndan

0.13

gamber

0.13

 Associates

0.13

Activations Density 0.085%

years and dates associated with events or changes in position

No Comments

No Known Activations