INDEX

Explanations

geographical names and locations, particularly those related to the United States and its cities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

uÅŁ

-0.17

ud

-0.15

èĪ¬

-0.14

Ð´Ñı

-0.13

asion

-0.13

pon

-0.13

igor

-0.13

ØªØ±ÛĮ

-0.13

è©²

-0.13

ï¼ģï¼ģ↵↵

-0.13

POSITIVE LOGITS

 Aires

0.18

 Pradesh

0.17

icana

0.16

 Dhabi

0.15

 York

0.15

 Janeiro

0.14

_Final

0.14

 Zealand

0.14

 Hampshire

0.14

Activations Density 0.109%

geographical names and locations, particularly those related to the United States and its cities

No Comments

No Known Activations