INDEX

Explanations

references to the Nissan car brand and its models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

MBER

-0.15

asta

-0.15

 Tibetan

-0.14

ÄįÃŃ

-0.14

 Worcester

-0.14

Sto

-0.14

 Minnesota

-0.14

*>*

-0.14

CRY

-0.14

beit

-0.14

POSITIVE LOGITS

 Nissan

0.29

 Sunderland

0.27

 Leaf

0.21

issan

0.20

Mur

0.19

 Sent

0.19

 Titan

0.19

Leaf

0.18

NV

0.18

Activations Density 0.014%

references to the Nissan car brand and its models

No Comments

No Known Activations