INDEX

Explanations

references to programming libraries and APIs, particularly in the context of Windows and ctypes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

imers

-0.17

elia

-0.16

 sens

-0.16

 Sanford

-0.15

/welcome

-0.15

emean

-0.14

ormsg

-0.14

reate

-0.14

 rare

-0.14

uses

-0.14

POSITIVE LOGITS

 VerfÃ¼g

0.15

 fisse

0.15

bundle

0.14

/WebAPI

0.14

ipel

0.14

 (!((

0.14

ffi

0.14

tog

0.14

arra

0.14

ayer

0.14

Activations Density 0.050%

references to programming libraries and APIs, particularly in the context of Windows and ctypes

No Comments

No Known Activations