INDEX

Explanations

phrases related to settling down or making commitments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

nis

-0.18

esis

-0.17

nine

-0.16

nos

-0.16

ermann

-0.15

soever

-0.15

dra

-0.15

rupa

-0.15

ÐµÐ½ÐºÐ°

-0.15

kem

-0.15

POSITIVE LOGITS

sett

0.23

 settling

0.23

tle

0.22

 settle

0.22

 settles

0.21

 settled

0.20

-down

0.20

 accounts

0.17

 Accounts

0.17

 nerves

0.17

Activations Density 0.014%

phrases related to settling down or making commitments

No Comments

No Known Activations