INDEX

Explanations

references to "cat" or related themes involving cats

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

gaard

-0.18

ourt

-0.18

 Citadel

-0.18

orer

-0.17

steen

-0.17

ureka

-0.16

 Atmos

-0.15

chia

-0.15

uppies

-0.15

POSITIVE LOGITS

apult

0.33

Ã©gorie

0.30

nip

0.28

amar

0.27

amount

0.23

fish

0.22

walk

0.22

elog

0.21

calls

0.21

enary

0.21

Activations Density 0.015%

references to "cat" or related themes involving cats

No Comments

No Known Activations