INDEX

Explanations

references to "ponies" and related terms

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

oq

-0.15

esk

-0.15

erÃ§

-0.15

ODE

-0.15

oop

-0.15

gne

-0.15

iales

-0.14

Äĥr

-0.14

ÑĢÐ¸Ð·

-0.14

ALSE

-0.14

POSITIVE LOGITS

pon

0.25

pon

0.22

Pon

0.21

pons

0.18

emon

0.18

yp

0.16

eder

0.16

poz

0.16

entially

0.16

cho

0.15

Activations Density 0.007%

references to "ponies" and related terms

No Comments

No Known Activations