INDEX

Explanations

mathematical terms and notation related to functions and continuity

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

ento

-0.17

áº¬

-0.15

rello

-0.14

 McKay

-0.14

 foil

-0.14

iene

-0.14

æĳĨ

-0.14

encing

-0.14

rita

-0.13

Ľ

-0.13

POSITIVE LOGITS

Topology

0.24

 Haus

0.22

 topology

0.22

compact

0.22

 compact

0.21

met

0.21

 Compact

0.21

Top

0.20

_topology

0.20

sequential

0.19

Activations Density 0.059%

mathematical terms and notation related to functions and continuity

No Comments

No Known Activations