INDEX

Explanations

specific place names and related geographic references

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

isclosed

-0.16

inja

-0.15

cope

-0.14

uÃ©

-0.14

harma

-0.13

kaar

-0.13

 Mund

-0.13

cliffe

-0.13

 Coal

-0.13

.rb

-0.13

POSITIVE LOGITS

 restaur

0.23

 conserv

0.20

co

0.18

 Conserv

0.18

fab

0.17

lap

0.17

 ligne

0.17

 datab

0.17

 monument

0.17

ÐµÐ³Ð¾ÑĢ

0.17

Activations Density 0.006%

specific place names and related geographic references

No Comments

No Known Activations