INDEX

Explanations

terminology and concepts related to strategic games, particularly chess

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

asca

-0.15

isia

-0.14

gate

-0.14

uve

-0.14

AdapterFactory

-0.14

ÑĢÐ°ÑīÐµÐ½Ð¸Ñı

-0.14

urope

-0.13

gos

-0.13

ä»°

-0.13

 elit

-0.13

POSITIVE LOGITS

 thematic

0.17

 pressure

0.16

 diagonal

0.16

 Wass

0.16

 Pills

0.15

uns

0.15

 Replies

0.15

 reply

0.14

acon

0.14

tring

0.14

Activations Density 0.003%

terminology and concepts related to strategic games, particularly chess

No Comments

No Known Activations