INDEX

Explanations

complex and nuanced discussions about fairness and politics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

achte

-0.17

 Responsive

-0.15

 inconsistent

-0.14

 cohesive

-0.14

 responsiveness

-0.14

Sensitive

-0.14

 incompetent

-0.14

\Lib

-0.14

 Resident

-0.14

Responsive

-0.14

POSITIVE LOGITS

 univers

0.23

 wholes

0.23

 explos

0.23

 predict

0.22

avity

0.21

iveness

0.21

ailability

0.21

nown

0.21

lessness

0.20

 heav

0.20

Activations Density 0.498%

complex and nuanced discussions about fairness and politics

No Comments

No Known Activations