INDEX

Explanations

references to the Python programming language and its associated concepts or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ilm

-0.19

 incel

-0.16

ÑĪÐºÑĥ

-0.15

esin

-0.15

lue

-0.15

mpar

-0.15

Gor

-0.15

-python

-0.14

Glo

-0.14

lass

-0.14

POSITIVE LOGITS

 Imaging

0.19

ic

0.19

hton

0.19

Anywhere

0.19

 interpreter

0.18

Interpreter

0.17

ista

0.17

 Launcher

0.17

ï»¿#

0.16

Activations Density 0.014%

references to the Python programming language and its associated concepts or features

No Comments

No Known Activations