INDEX

Explanations

names of places and geographical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 cons

-0.18

anners

-0.17

ause

-0.15

aks

-0.15

ast

-0.15

ok

-0.15

 neur

-0.14

´

-0.14

lo

-0.14

ars

-0.14

POSITIVE LOGITS

ylim

0.18

_Impl

0.16

 GÃ¼ven

0.16

itÃł

0.16

hest

0.16

yonel

0.16

zej

0.15

ÅŁk

0.15

ografia

0.15

 Opport

0.15

Activations Density 0.105%

names of places and geographical terms

No Comments

No Known Activations