INDEX

Explanations

terms related to horses and horseback riding activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

eration

-0.17

erset

-0.16

repid

-0.15

enance

-0.15

ERM

-0.15

lain

-0.14

ewriter

-0.14

Lob

-0.14

toArray

-0.14

.iterator

-0.14

POSITIVE LOGITS

back

0.32

hair

0.29

men

0.26

play

0.25

power

0.24

BACK

0.23

 drawn

0.22

women

0.21

fly

0.21

hoe

0.21

Activations Density 0.013%

terms related to horses and horseback riding activities

No Comments

No Known Activations