INDEX

Explanations

mentions of locations and geographic features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 addCriterion

-0.19

ellas

-0.17

ellular

-0.15

ÐµÑģÐ°

-0.15

antium

-0.15

arme

-0.15

inya

-0.15

 Dense

-0.15

landers

-0.15

lands

-0.14

POSITIVE LOGITS

 town

0.35

 small

0.28

 capital

0.27

 resort

0.27

 port

0.25

small

0.21

çĶº

0.21

 seaside

0.20

 city

0.20

spa

0.19

Activations Density 0.139%

mentions of locations and geographic features

No Comments

No Known Activations