INDEX

Explanations

information about geographical entities and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

umbed

-0.15

urus

-0.15

ifen

-0.15

CLUDING

-0.15

eka

-0.14

arrow

-0.14

 persecuted

-0.14

.CodeAnalysis

-0.13

oko

-0.13

oka

-0.13

POSITIVE LOGITS

 home

0.41

home

0.30

-home

0.26

(home

0.25

 Home

0.23

Home

0.23

 HOME

0.23

_home

0.22

ge

0.22

 host

0.21

Activations Density 0.104%

information about geographical entities and their characteristics

No Comments

No Known Activations