INDEX

Explanations

mentions of academic achievements and professional titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

udo

-0.15

 Ngá»įc

-0.15

ÑĦÐ°

-0.14

 Exodus

-0.14

 ê°Ĳëıħ

-0.14

NGC

-0.13

blo

-0.13

_IMPLEMENT

-0.13

gorm

-0.13

ette

-0.13

POSITIVE LOGITS

 Learned

0.24

 Royal

0.24

Royal

0.23

AA

0.22

 academy

0.22

 Fellow

0.22

 foreign

0.22

 elected

0.21

 Fell

0.21

 election

0.21

Activations Density 0.038%

mentions of academic achievements and professional titles

No Comments

No Known Activations