INDEX

Explanations

references to specific BMW models and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

FX

-0.16

 Essex

-0.15

tingham

-0.15

 Maduro

-0.15

afari

-0.14

pecia

-0.14

strup

-0.14

amÄ±z

-0.14

Äįel

-0.14

Î¹ÎºÏĮÏĤ

-0.14

POSITIVE LOGITS

BMW

0.35

bm

0.30

BMW

0.28

bm

0.28

Bav

0.27

 Munich

0.27

BM

0.26

 MÃ¼nchen

0.25

BM

0.23

 Efficient

0.21

Activations Density 0.079%

references to specific BMW models and their features

No Comments

No Known Activations