INDEX

Explanations

references to awards or achievements in competitive contexts

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

-0.17

ell

-0.15

ansen

-0.14

 typical

-0.13

cott

-0.13

Brun

-0.13

 cult

-0.13

.dateTime

-0.13

ike

-0.13

 éĺ

-0.13

POSITIVE LOGITS

iland

0.16

Ð°Ð½Ð¸ÑĨ

0.15

habi

0.15

_soft

0.15

ifax

0.14

 addCriterion

0.14

å±ĭ

0.14

zier

0.14

OMPI

0.14

udes

0.14

Activations Density 0.018%

references to awards or achievements in competitive contexts

No Comments

No Known Activations