INDEX

Explanations

references to programming concepts and application development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 yourself

-0.17

 even

-0.15

NonNull

-0.14

_even

-0.13

ardless

-0.13

 navÃŃc

-0.13

 EVEN

-0.13

$core

-0.13

 yourselves

-0.13

YOU

-0.13

POSITIVE LOGITS

 recently

0.25

 lately

0.22

 Recently

0.20

 spor

0.19

 need

0.19

 occasionally

0.18

recent

0.18

 intermitt

0.18

Recently

0.18

 currently

0.18

Activations Density 0.202%

references to programming concepts and application development

No Comments

No Known Activations