INDEX

Explanations

phrases related to filtering data and managing complex relationships in datasets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

usp

-0.14

corr

-0.13

mary

-0.13

imits

-0.13

 Truy

-0.13

ëĶĶìĭľ

-0.13

 McGregor

-0.12

adil

-0.12

aepernick

-0.12

POSITIVE LOGITS

 only

0.25

but

0.21

ä»¥å¤ĸ

0.19

only

0.19

 twice

0.17

 until

0.17

 differently

0.16

 ONLY

0.16

agal

0.16

_only

0.16

Activations Density 1.328%

phrases related to filtering data and managing complex relationships in datasets

No Comments

No Known Activations