INDEX

Explanations

phrases related to advice and feedback-seeking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

arp

-0.16

kÃ¼

-0.15

bjerg

-0.15

oland

-0.15

rapper

-0.14

imax

-0.14

azine

-0.14

uru

-0.14

sss

-0.14

å¿ľ

-0.13

POSITIVE LOGITS

 analysis

0.21

 advice

0.20

 observations

0.20

 opinion

0.20

 facts

0.20

 pictures

0.19

 debate

0.18

 opin

0.18

 direction

0.18

 experiences

0.18

Activations Density 0.214%

phrases related to advice and feedback-seeking

No Comments

No Known Activations