INDEX

Explanations

technical specifications and adjustable features in equipment

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

ivet

-0.15

.hr

-0.14

owan

-0.14

èĸ

-0.14

oxide

-0.14

oriented

-0.13

esen

-0.13

atatype

-0.13

ious

-0.13

flen

-0.13

POSITIVE LOGITS

 controlling

0.21

 controls

0.21

controlled

0.21

-controlled

0.21

 controlled

0.21

æİ§

0.19

 Controlled

0.18

-ranging

0.18

 control

0.18

 settings

0.18

Activations Density 0.183%

technical specifications and adjustable features in equipment

No Comments

No Known Activations