INDEX

Explanations

elements related to statistical or numerical data in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

æĻ´

-0.15

ienie

-0.15

ìĦ¸

-0.14

inya

-0.14

oup

-0.14

ISM

-0.14

ium

-0.14

gaard

-0.14

uja

-0.14

POSITIVE LOGITS

Ãłn

0.18

ãģį

0.16

 above

0.16

annel

0.16

 Ulus

0.14

itch

0.14

illi

0.14

bas

0.14

Ð°Ð»Ñĥ

0.14

above

0.14

Activations Density 0.103%

elements related to statistical or numerical data in a structured format

No Comments

No Known Activations