INDEX

Explanations

references to programming concepts and technical details in Python

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

RTOS

-0.16

å¤©

-0.16

ecut

-0.15

Ð°ÑĢÑı

-0.14

ingroup

-0.14

arkin

-0.14

omor

-0.14

burn

-0.14

 horns

-0.14

uely

-0.14

POSITIVE LOGITS

(PyObject

0.18

opy

0.17

Py

0.17

 PyObject

0.16

.python

0.16

 Python

0.16

ixe

0.15

_PY

0.15

 PyQt

0.15

Python

0.15

Activations Density 0.099%

references to programming concepts and technical details in Python

No Comments

No Known Activations