INDEX

Explanations

keywords indicating selection and types of data structures in 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

.bz

-0.18

buz

-0.17

azen

-0.17

.Dictionary

-0.15

errar

-0.15

ofire

-0.15

à¤Ńà¤Ĺ

-0.14

ĮĢ

-0.14

alse

-0.14

PROTO

-0.14

POSITIVE LOGITS

raq

0.17

cht

0.16

Runnable

0.15

oug

0.15

 ownerId

0.15

ym

0.15

yg

0.15

ante

0.15

ulos

0.14

Vil

0.14

Activations Density 0.039%

keywords indicating selection and types of data structures in programming context

No Comments

No Known Activations