INDEX

Explanations

mentions of educational institutions and schools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Mom

-0.17

ÙĪÙĨØ¯

-0.16

Ø§ÙĤÙĦ

-0.15

ÏĦÏģ

-0.14

 Highlander

-0.13

reste

-0.13

Ð©

-0.13

apa

-0.13

 hass

-0.13

trait

-0.13

POSITIVE LOGITS

 Secondary

0.29

 secondary

0.29

 primaries

0.27

Secondary

0.27

 Primary

0.25

 primary

0.25

secondary

0.25

imary

0.25

 maintained

0.24

 Reception

0.24

Activations Density 0.087%

mentions of educational institutions and schools

No Comments

No Known Activations