INDEX

Explanations

the occurrences of the word "bab" or its variations, indicating a focus on familial or affectionate terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

yen

-0.20

-0.18

rowable

-0.17

yu

-0.17

mite

-0.16

uario

-0.15

IGHT

-0.15

yah

-0.15

hee

-0.15

yas

-0.15

POSITIVE LOGITS

ylon

0.30

cock

0.30

bling

0.27

oons

0.23

ble

0.22

ette

0.21

raham

0.21

blers

0.21

oon

0.20

elf

0.20

Activations Density 0.007%

the occurrences of the word "bab" or its variations, indicating a focus on familial or affectionate terms

No Comments

No Known Activations

the occurrences of the word "bab" or its variations, indicating a focus on familial or affectionate terms

No Comments

No Known Activations