INDEX

Explanations

mentions of geographic locations and places of interest, particularly related to tours and local history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

©

-0.17

uze

-0.15

spinner

-0.15

InputBorder

-0.15

egen

-0.14

Brief

-0.14

PUR

-0.14

feld

-0.14

Ð³Ð°Ð»

-0.14

utschein

-0.13

POSITIVE LOGITS

 street

0.20

street

0.18

 streets

0.17

 city

0.15

ãĥ³ãĥ

0.15

Street

0.15

aki

0.15

 Cleveland

0.15

è¡Ĺ

0.14

 Farr

0.14

Activations Density 0.699%

mentions of geographic locations and places of interest, particularly related to tours and local history

No Comments

No Known Activations