INDEX

Explanations

details relating to events and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ahi

-0.15

isher

-0.15

onto

-0.15

Alternate

-0.14

Î´Ïİ

-0.14

 acre

-0.14

enaire

-0.14

 Olymp

-0.14

oven

-0.13

ETO

-0.13

POSITIVE LOGITS

ettle

0.15

ÑħÑĥ

0.15

ardu

0.15

 similarly

0.14

rico

0.14

/autoload

0.14

 also

0.14

also

0.14

 ocksÃ¥

0.14

Ã¢m

0.14

Activations Density 1.346%

details relating to events and achievements

No Comments

No Known Activations