INDEX

Explanations

phrases related to subscription services and calls to action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

wen

-0.17

stride

-0.17

beck

-0.16

chet

-0.16

stri

-0.16

ight

-0.16

sten

-0.15

-0.14

AutoSize

-0.14

 prost

-0.14

POSITIVE LOGITS

.unsubscribe

0.21

tember

0.18

issement

0.17

istar

0.17

/un

0.16

ERG

0.16

ption

0.16

 unsubscribe

0.15

/lic

0.15

avers

0.15

Activations Density 0.009%

phrases related to subscription services and calls to action

No Comments

No Known Activations