INDEX

Explanations

terms related to archaeology and archaeological studies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

itsu

-0.16

ARP

-0.15

ccoli

-0.15

Ã¡Å¡

-0.15

ÏĥÏĩ

-0.14

Ã¨s

-0.14

til

-0.14

akter

-0.14

ulong

-0.13

POSITIVE LOGITS

tracts

0.17

 Lange

0.16

èĩ£

0.15

ervas

0.15

ãĥªãĥ¼ãĤº

0.14

erti

0.14

ÏģÎ¹Ïĥ

0.14

Ø²Ø§Ø¯Ùĩ

0.13

.tele

0.13

 OMIT

0.13

Activations Density 0.006%

terms related to archaeology and archaeological studies

No Comments

No Known Activations