INDEX

Explanations

formal mathematical constructs and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 hypothesis

-0.16

bab

-0.14

 humble

-0.14

 asympt

-0.13

entionPolicy

-0.13

Abb

-0.13

_dat

-0.13

ych

-0.13

POSITIVE LOGITS

 analytical

0.37

 analytic

0.33

 closed

0.32

 analy

0.31

analy

0.30

 Closed

0.30

 expressions

0.30

closed

0.29

Closed

0.28

 exact

0.28

Activations Density 0.243%

formal mathematical constructs and terminology

No Comments

No Known Activations