INDEX

Explanations

questions about preferences and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ault

-0.20

lice

-0.18

esign

-0.17

eting

-0.15

ipay

-0.14

omet

-0.14

idget

-0.13

Talking

-0.13

lic

-0.13

ptide

-0.13

POSITIVE LOGITS

 then

0.27

 Then

0.23

 entonces

0.23

Then

0.22

then

0.20

	then

0.20

_then

0.20

 THEN

0.19

 ÑĤÐ¾Ð³Ð´Ð°

0.18

THEN

0.18

Activations Density 0.067%

questions about preferences and experiences

No Comments

No Known Activations