INDEX

Explanations

phrases and terms related to social issues and discussions surrounding systemic problems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 hale

-0.16

-wise

-0.15

 wise

-0.15

 Harmony

-0.15

Venue

-0.14

imir

-0.14

.getOwnProperty

-0.14

ALLY

-0.13

wise

-0.13

POSITIVE LOGITS

 phenomenon

0.31

 syndrome

0.30

 thing

0.29

 Syndrome

0.26

 Principle

0.24

 principle

0.24

 phenomena

0.23

 theory

0.23

 hypothesis

0.23

 Thing

0.23

Activations Density 0.295%

phrases and terms related to social issues and discussions surrounding systemic problems

No Comments

No Known Activations