INDEX

Explanations

elements related to structures and organization in texts

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

 actual

-0.15

ogi

-0.14

amar

-0.14

 ÑĪÑĤ

-0.14

 Jarvis

-0.13

 è¡

-0.13

ModelProperty

-0.13

 Raymond

-0.13

 updates

-0.13

(s

-0.13

POSITIVE LOGITS

 vidÃ©o

0.19

 TMPro

0.18

áº£o

0.14

appropriate

0.14

 interview

0.14

 videos

0.14

="__

0.14

.lesson

0.14

unger

0.14

 Ð²Ð¸Ð´Ðµ

0.14

Activations Density 0.003%

elements related to structures and organization in texts

No Comments

No Known Activations