INDEX

Explanations

references to forms and application processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

olit

-0.16

kova

-0.15

mens

-0.15

CAD

-0.14

il

-0.14

pip

-0.13

Ð¾Ð»Ð¸ÑĤ

-0.13

 bread

-0.13

outs

-0.13

POSITIVE LOGITS

 Forms

0.20

 forms

0.19

forms

0.17

/forms

0.16

HEET

0.15

#ad

0.15

 å¡

0.15

Forms

0.15

å¡«

0.15

ulas

0.15

Activations Density 0.039%

references to forms and application processes

No Comments

No Known Activations