INDEX

Explanations

occurrences of the word "unt" or variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ROME

-0.16

icine

-0.15

leta

-0.15

lette

-0.15

/tos

-0.15

macros

-0.15

rico

-0.14

 Brah

-0.14

########

-0.14

agher

-0.14

POSITIVE LOGITS

ouch

0.34

old

0.32

oward

0.31

ether

0.31

angling

0.30

apped

0.29

idy

0.28

amed

0.27

ainted

0.26

arn

0.26

Activations Density 0.006%

occurrences of the word "unt" or variations of it

No Comments

No Known Activations