INDEX

Explanations

references to meals 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Prem

-0.15

 alle

-0.15

 Mood

-0.14

ermann

-0.14

.proxy

-0.14

 Expl

-0.13

avana

-0.13

æµ¦

-0.13

 Material

-0.13

alle

-0.13

POSITIVE LOGITS

 lunch

0.43

 dinner

0.39

 meals

0.36

 breakfast

0.35

 Lunch

0.34

 meal

0.31

 Dinner

0.30

 lunches

0.28

 Breakfast

0.27

 supper

0.24

Activations Density 0.217%

references to meals and dining experiences

No Comments

No Known Activations