INDEX

Explanations

references to historical data, studies, or key financial years related to economic theories and developments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

enting

-0.19

Éµ

-0.17

longleftrightarrow

-0.16

itos

-0.16

apgolly

-0.14

Ð»Ð°ÑĪ

-0.14

isol

-0.14

visor

-0.14

opak

-0.14

olik

-0.14

POSITIVE LOGITS

 Brend

0.14

 suff

0.14

ft

0.14

erli

0.14

 coin

0.14

eu

0.14

 acceler

0.13

inv

0.13

 coerc

0.13

ŃĲï¸ı

0.13

Activations Density 0.030%

references to historical data, studies, or key financial years related to economic theories and developments

No Comments

No Known Activations