INDEX

Explanations

elements and their relations in a data structure related to a programming context

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

led

-0.18

ernel

-0.17

nad

-0.15

ÐĬ

-0.14

erver

-0.14

 Mare

-0.14

ledon

-0.14

eg

-0.14

mani

-0.14

(s

-0.13

POSITIVE LOGITS

igrations

0.15

udas

0.15

apture

0.14

 ninh

0.14

atron

0.14

apur

0.13

imir

0.13

/Foundation

0.13

Ù¾Ø³

0.13

 teÅŁkil

0.13

Activations Density 0.231%

elements and their relations in a data structure related to a programming context

No Comments

No Known Activations