INDEX

Explanations

phrases related to conclusions and endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

oenix

-0.17

utow

-0.16

intage

-0.16

quez

-0.16

 minded

-0.16

duck

-0.15

-minded

-0.15

chten

-0.15

odos

-0.15

âĢĮØ´Ø¯Ùĩ

-0.15

POSITIVE LOGITS

owment

0.34

urance

0.28

earing

0.28

angered

0.27

orse

0.27

ogenous

0.26

/start

0.26

ereÃ§o

0.26

orses

0.26

ocrine

0.25

Activations Density 0.100%

phrases related to conclusions and endings

No Comments

No Known Activations