INDEX

Explanations

geographical locations and cities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

onth

-0.15

 mechan

-0.14

isposable

-0.14

 Cham

-0.14

 landing

-0.13

ponsible

-0.13

 Baghdad

-0.13

ãĤħ

-0.13

/XMLSchema

-0.13

åŃ¦ä¼ļ

-0.13

POSITIVE LOGITS

 à¸Ľà¸£à¸°à¹Ģà¸Ĺà¸¨

0.15

stor

0.15

ervo

0.15

-based

0.15

ezi

0.15

Ã©n

0.14

imas

0.14

ł

0.14

ognito

0.14

-Based

0.14

Activations Density 0.064%

geographical locations and cities

No Comments

No Known Activations