INDEX

Explanations

references to food and dining 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulo

-0.16

 sequ

-0.15

 cogn

-0.15

 base

-0.14

fn

-0.14

int

-0.13

çŃ

-0.13

Ð±Ð¾Ð¼

-0.13

elow

-0.13

USR

-0.13

POSITIVE LOGITS

 takeaway

0.28

 take

0.24

 carry

0.23

 Take

0.23

 TAKE

0.23

 Carry

0.22

take

0.21

_take

0.21

Take

0.21

carry

0.20

Activations Density 0.091%

references to food and dining experiences

No Comments

No Known Activations