INDEX

Explanations

occurrences of the word "rum" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

arth

-0.19

ARTH

-0.15

canf

-0.15

$l

-0.15

lijke

-0.15

iol

-0.14

iving

-0.14

anic

-0.14

áº±m

-0.14

anik

-0.14

POSITIVE LOGITS

rum

0.27

oured

0.25

ination

0.24

Rum

0.23

pled

0.23

blings

0.23

rum

0.21

ored

0.20

mage

0.20

bling

0.20

Activations Density 0.005%

occurrences of the word "rum" in various forms

No Comments

No Known Activations