INDEX

Explanations

terms and phrases related to archaeology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

gu

-0.16

rol

-0.15

 hosp

-0.15

ì§ĵ

-0.15

antes

-0.14

Ã¶z

-0.14

trap

-0.14

roke

-0.14

ser

-0.14

recht

-0.14

POSITIVE LOGITS

 excav

0.21

Exc

0.20

 digs

0.20

Exc

0.19

 Site

0.18

 sites

0.18

oa

0.18

exc

0.17

Sites

0.17

-exc

0.17

Activations Density 0.007%

terms and phrases related to archaeology

No Comments

No Known Activations