INDEX

Explanations

references to object attributes and properties in 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

rana

-0.17

ibe

-0.16

Ð½Ð¾Ð²Ð°

-0.15

.dispatch

-0.15

atl

-0.15

ipo

-0.15

iring

-0.14

ÑĤÑı

-0.14

ÙĬÙĦØ©

-0.14

engin

-0.14

POSITIVE LOGITS

arin

0.17

two

0.16

ssf

0.15

urum

0.15

.ajax

0.15

ëĳĲ

0.14

_TWO

0.14

commons

0.14

arsing

0.14

 three

0.14

Activations Density 0.153%

references to object attributes and properties in a programming context

No Comments

No Known Activations