INDEX

Explanations

instances of reporting or narration related to personal stories or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 nomine

-0.15

Ø§ÙħØ©

-0.14

enth

-0.14

viso

-0.14

usp

-0.13

iner

-0.13

 Stranger

-0.13

.grpc

-0.13

ÅŁa

-0.13

ipse

-0.13

POSITIVE LOGITS

 joining

0.24

 joins

0.22

Join

0.22

 Join

0.20

joining

0.20

 Transcript

0.20

 reporting

0.20

 join

0.19

join

0.18

 Reporting

0.17

Activations Density 0.028%

instances of reporting or narration related to personal stories or experiences

No Comments

No Known Activations