INDEX

Explanations

references to specific car models and brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ltra

-0.18

buz

-0.17

 Ø°

-0.16

anime

-0.15

 pBuffer

-0.15

_SUS

-0.14

 Hindered

-0.14

Ð¾ÐºÐ¾Ð½

-0.14

obus

-0.14

Ã»

-0.14

POSITIVE LOGITS

 Ford

0.35

Ford

0.30

 Chicago

0.24

Chicago

0.21

 Mustang

0.21

 Lincoln

0.20

 ford

0.20

 Illinois

0.19

 SYNC

0.18

 Shelby

0.18

Activations Density 0.011%

references to specific car models and brands

No Comments

No Known Activations