INDEX

Explanations

programming-related terms and objects within a code context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

rea

-0.17

Ã³j

-0.15

quate

-0.15

idge

-0.14

oment

-0.14

bourg

-0.14

quoise

-0.14

.logged

-0.14

.Slf

-0.14

metry

-0.14

POSITIVE LOGITS

ancial

0.16

engu

0.14

auer

0.13

mpar

0.13

auga

0.13

.ft

0.13

ÑģÐ¾Ð»

0.13

erdale

0.13

 Nose

0.13

Activations Density 0.048%

programming-related terms and objects within a code context

No Comments

No Known Activations