INDEX

Explanations

references to coding platforms and tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 çı

-0.16

ace

-0.15

anse

-0.15

isp

-0.14

 ÙħØ²

-0.14

Ø±Ø¯

-0.14

uble

-0.14

ansi

-0.14

chÃ©

-0.14

noop

-0.14

POSITIVE LOGITS

vÄĽd

0.15

peater

0.15

hiro

0.14

 Ð£ÐºÑĢÐ°ÑĹ

0.14

HashCode

0.14

.net

0.14

_fu

0.14

à¹ģà¸ľ

0.14

idor

0.14

#else

0.14

Activations Density 0.006%

references to coding platforms and tools

No Comments

No Known Activations