INDEX

Explanations

references to oaths and vows, particularly in a context involving love and commitment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

å¡

-0.18

rana

-0.14

quier

-0.14

itzer

-0.14

ernel

-0.14

 Perr

-0.14

witter

-0.13

ÑĥÐ·

-0.13

ojis

-0.13

oes

-0.13

POSITIVE LOGITS

 oath

0.27

 allegiance

0.25

 sworn

0.23

 swearing

0.19

 swore

0.19

 vows

0.18

 swear

0.18

 binds

0.18

 pled

0.17

 pledge

0.17

Activations Density 0.032%

references to oaths and vows, particularly in a context involving love and commitment

No Comments

No Known Activations