INDEX

Explanations

words and phrases related to circuses and circuses' thematic elements

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

ifar

-0.16

 COPYING

-0.15

å°ĸ

-0.15

ffa

-0.15

oug

-0.14

halt

-0.14

UPLE

-0.14

agnostic

-0.14

_CAPTURE

-0.14

lord

-0.14

POSITIVE LOGITS

 Circ

0.29

circ

0.28

 circuit

0.28

uits

0.27

 circ

0.27

 circum

0.25

 circuits

0.24

adian

0.24

 Circuit

0.23

cir

0.22

Activations Density 0.010%

words and phrases related to circuses and circuses' thematic elements

No Comments

No Known Activations

words and phrases related to circuses and circuses' thematic elements

No Comments

No Known Activations