INDEX

Explanations

references to specific locations and tourism-related information

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

 Chennai

-0.17

æµľ

-0.17

 Baltimore

-0.16

 Giang

-0.16

 Fior

-0.16

-0.15

 Rutgers

-0.15

 Zheng

-0.15

 Malaysia

-0.15

 Tamil

-0.15

POSITIVE LOGITS

 Wyoming

0.69

Wy

0.51

 Yellowstone

0.44

wy

0.41

Wy

0.39

 Cowboy

0.39

 Cody

0.38

 Sheridan

0.36

 Uint

0.35

wy

0.34

Activations Density 0.021%

references to specific locations and tourism-related information

No Comments

No Known Activations