INDEX

Explanations

references to geographical features and landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 downstairs

-0.17

alytics

-0.17

»¿

-0.16

 Mobil

-0.15

 downstream

-0.14

 Epidemi

-0.14

 Shore

-0.14

 æ¬

-0.14

æº

-0.14

ouro

-0.14

POSITIVE LOGITS

 hill

0.38

 peak

0.35

 summit

0.33

hil

0.29

 peaks

0.29

 mount

0.28

 Hill

0.28

 ridge

0.28

 hills

0.27

å³°

0.27

Activations Density 0.138%

references to geographical features and landmarks

No Comments

No Known Activations