INDEX

Explanations

mentions of geographic locations, specifically those related to the East

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ity

-0.15

illance

-0.15

lect

-0.15

 volta

-0.14

osoph

-0.14

 mortal

-0.14

iselect

-0.13

à¤¿à¤¡

-0.13

LOCK

-0.13

rary

-0.13

POSITIVE LOGITS

ablish

0.24

ward

0.21

ern

0.20

side

0.19

gard

0.18

à¹Ģà¸ī

0.17

shot

0.16

wing

0.16

rough

0.15

ensibly

0.15

Activations Density 0.027%

mentions of geographic locations, specifically those related to the East

No Comments

No Known Activations