INDEX

Explanations

geographical locations and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 dane

-0.14

.ready

-0.14

etat

-0.14

ëĭ¤ê°Ģ

-0.14

antes

-0.13

/Private

-0.13

ench

-0.13

irez

-0.13

Bloc

-0.13

äºŃ

-0.13

POSITIVE LOGITS

-sur

0.22

erland

0.19

ensis

0.19

ense

0.17

 city

0.17

ecko

0.16

enses

0.16

intColor

0.16

 municipality

0.16

 CreateTable

0.15

Activations Density 0.119%

geographical locations and related terms

No Comments

No Known Activations