INDEX

Explanations

references to national parks and tourism-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ainen

-0.17

lad

-0.16

builtin

-0.15

loom

-0.14

æµľ

-0.14

lesc

-0.14

 à¤¤à¤®

-0.14

 Zheng

-0.14

Md

-0.14

POSITIVE LOGITS

 Wyoming

0.54

Wy

0.42

wy

0.35

 Sheridan

0.34

 Yellowstone

0.32

Cas

0.31

wy

0.30

Wy

0.30

 Cody

0.29

 Cowboy

0.29

Activations Density 0.019%

references to national parks and tourism-related activities

No Comments

No Known Activations