INDEX

Explanations

terms related to professional services and partnerships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

eros

-0.17

ucken

-0.16

 Russo

-0.15

imeo

-0.15

.uf

-0.14

lev

-0.14

rad

-0.14

éķĩ

-0.14

osate

-0.14

à¸²à¸¢

-0.14

POSITIVE LOGITS

0.17

inish

0.15

itez

0.14

ToMany

0.14

 INTERRUPTION

0.14

ÏĥÏĩ

0.13

ãģªãĤĭ

0.13

.synthetic

0.13

ukan

0.13

Activations Density 0.133%

terms related to professional services and partnerships

No Comments

No Known Activations