INDEX

Explanations

language related to evaluation and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cop

-0.16

oon

-0.16

ÙĦØ©

-0.16

ovit

-0.14

/validation

-0.14

Ø¯Ø§Ø´Øª

-0.14

stoupil

-0.14

å£«

-0.14

itet

-0.14

à¥ģà¤§

-0.14

POSITIVE LOGITS

 weighed

0.38

 weighing

0.37

weigh

0.37

 weigh

0.37

 benefits

0.34

 outweigh

0.32

 risks

0.32

 balancing

0.31

 risk

0.31

 balance

0.30

Activations Density 0.219%

language related to evaluation and decision-making processes

No Comments

No Known Activations