INDEX

Explanations

references to visual characteristics and rendering in graphics or display contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 comp

-0.15

AAF

-0.15

ekk

-0.14

fl

-0.14

 court

-0.14

 Ø³Ø¹

-0.14

 ëĵľ

-0.13

abus

-0.13

 Buzz

-0.13

 quint

-0.13

POSITIVE LOGITS

 Terminal

0.21

 terminal

0.20

 ConsoleColor

0.20

ansi

0.18

Terminal

0.18

 terminals

0.18

oux

0.18

 interactive

0.18

terminal

0.17

_terminal

0.17

Activations Density 0.051%

references to visual characteristics and rendering in graphics or display contexts

No Comments

No Known Activations