INDEX

Explanations

phrases indicating possession or requests for information

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

ogn

-0.15

ano

-0.14

uced

-0.14

omm

-0.14

sher

-0.14

ÏĩÎ½

-0.14

isk

-0.14

 Ð¾ÑĤÐºÐ°Ð·

-0.13

 demise

-0.13

atis

-0.13

POSITIVE LOGITS

 questions

0.32

 Questions

0.26

 ever

0.25

questions

0.24

any

0.23

Questions

0.21

 experience

0.20

 Fragen

0.19

 trouble

0.19

 concerns

0.19

Activations Density 0.088%

phrases indicating possession or requests for information

No Comments

No Known Activations