INDEX

Explanations

references to geographical locations and specific entities related to them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

sz

-0.16

Ä±s

-0.16

_sz

-0.15

 Proxy

-0.15

oulos

-0.14

Kov

-0.14

 Egyptian

-0.14

 Toronto

-0.14

SZ

-0.14

 Egyptians

-0.14

POSITIVE LOGITS

 Guam

0.39

Pago

0.22

 Samoa

0.19

 Pacific

0.19

 Marian

0.17

Pacific

0.17

Mic

0.16

-Pacific

0.16

Asia

0.16

 Honolulu

0.16

Activations Density 0.008%

references to geographical locations and specific entities related to them

No Comments

No Known Activations