INDEX

Explanations

names of cities and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Albania

-0.16

iris

-0.14

zas

-0.14

 Rhode

-0.14

tip

-0.14

 Prec

-0.14

 Slovakia

-0.14

åº§

-0.14

.PNG

-0.13

 flock

-0.13

POSITIVE LOGITS

 London

0.17

Ð»Ð°Ð·

0.17

 cities

0.17

ucu

0.16

ige

0.16

London

0.15

 Cities

0.14

 ÐŀÑģÑĤ

0.14

åŁİå¸Ĥ

0.14

ureka

0.14

Activations Density 0.065%

names of cities and locations

No Comments

No Known Activations