INDEX

Explanations

references to organizational issues and critiques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Brisbane

-0.21

 Kuala

-0.19

 Honolulu

-0.19

 Winnipeg

-0.18

Seattle

-0.17

ä½

-0.16

 Queensland

-0.16

 Saras

-0.16

 Worcester

-0.16

Houston

-0.16

POSITIVE LOGITS

NY

0.39

 Giants

0.36

 Knicks

0.35

 Manhattan

0.34

NY

0.33

New

0.32

NYC

0.31

 Giant

0.31

 NYPD

0.29

Eli

0.29

Activations Density 0.033%

references to organizational issues and critiques

No Comments

No Known Activations